Index

• $\vDash ̸$ (not entails) §5.1.2
• $\leftarrow$ (if) 2nd item, Figure 5.1, 2nd item, 2nd item
• $\to$ (implies) Figure 5.1, 2nd item
• $\leftrightarrow$ (equivalence) Figure 5.1, 2nd item
• $=$ (equals) §15.8
• $\ne$ (not equal to) §15.8.2
• $\neg$ (not) Figure 5.1, 2nd item
• $\wedge$ (and) Figure 5.1, 2nd item, 2nd item
• $\vee$ (or) Figure 5.1, 2nd item
• $\oplus$ (exclusive-or) Figure 5.1, 2nd item
• $⊢$ (prove) §5.3.2
• $\perp$ (bottom) 3rd item
• $\vDash$ (entails) §15.3.2, §5.1.2
• $⟼$ (rewritten as) §15.7.1
• 0–1 loss 1st item
• $A^{\ast }$ search §3.6.1, §3.7.2
• abduction §5.8, §5.8
• abductive diagnosis §5.8
• abilities 5th item
• ableist §12.6
• ABox 2nd item
• absolute loss 2nd item
• absorbing state §12.5
• abstraction §1.6.4
• abundant homogenous data 2nd item
• accident §13.10
• accountability §18.3
• accuracy 1st item, §7.2.1
• achievement goal 1st item, 1st item
• acting intelligently §1.1
• action §2.1, §6.1
  • constraint §6.4.1
  • feature §6.4.1
  • function 4th item
  • instance §6.5
  • profile §14.2.1, §14.4
  • replay §13.9.1
  • variable 2nd item
• activation function §7.3.2, §8.1
• active learning item Online and offline
• active sensor 2nd item, §5.4
• acts §1.1
• actuator 2nd item
• acyclic directed graph (DAG) §3.3.1
• acyclic knowledge base §5.7
• Adam (optimizer) Table B.2, §8.2.3
• Adam (robot scientist) §15.10
• adaptive importance sampling §9.7.5
• additive independence §12.1.2
• additive utility §12.1.2
• adjective 2nd item
• admissible
  • heuristic 3rd item, §3.6, §3.6.3
  • search algorithm §3.6.1
• adversarial
  • debiasing §8.6.2
  • network §8.6.2
  • reasoning 2nd item, §14.3.1
• aerodynamics §1.2.1
• agent §1.1, §1.3, §2.1, §2.1
  • autonomous §1.3, Chapter 18
  • purposive §1.3
  • semi-autonomous §1.3, Chapter 18, §18.3
• aggregator §17.3.1
• AGI, see artificial general intelligence
• AI §1.1
• AI Act, see Artificial Intelligence Act
• AI ethics §18.7
  • for humans item A.
  • for systems item B.
• AIPython (aipython.org) Example 2.6, §4.11, New to This Edition
• AIspace §18.6
• algebraic variable §4.1.1
• algorithm
  • asynchronous value iteration Figure 12.18
  • boosting Figure 7.19
  • branch-and-bound
    • factored optimization Figure 4.12
  • collaborative filtering Figure 17.2
  • constraint satisfaction problem (CSP)
    • domain splitting Figure 4.6
    • generalized arc consistency Figure 4.4
  • Conv2D Figure 8.9
  • debugging
    • false positive Figure 5.6
    • missing answer Figure 5.7
  • decision tree learner Figure 7.9
  • depth-first
    • branch-and-bound Figure 3.14
    • CSP solver Figure 4.1
    • decision network optimization Figure 12.13
    • probabilistic inference Figure 9.9
    • search Figure 3.9
  • dropout Figure 8.7
  • expectation maximization (EM) Figure 10.8
  • game tree search Figure 14.5
  • genetic algorithm Figure 4.11
    • crossover 28
  • Gibbs sampling Figure 9.35
  • gradient-boosted trees Figure 7.21
  • iterative deepening Figure 3.11
  • k-means Figure 10.4
  • likelihood weighting Figure 9.33
  • local search Figure 4.8
  • logistic regression Figure 7.12
  • minimax with $\alpha$–$\beta$ pruning Figure 14.7
  • model-based reinforcement learning Figure 13.6
  • neural network
    • dense linear function Figure 8.3
    • stochastic gradient descent 15
  • partial-order planner Figure 6.6
  • particle filtering Figure 9.34
  • policy iteration Figure 12.19
  • proof procedure
    • conflict
      • bottom-up Figure 5.9
      • top-down Figure 5.10
    • Datalog
      • top-down Figure 15.5
    • definite clause
      • bottom-up Figure 5.3
      • top-down Figure 5.4
    • negation-as-failure
      • bottom-up Figure 5.11
      • top-down Figure 5.12
  • Q-learning Figure 13.3
  • recursive conditioning Figure 9.12
  • ReLU (neural network) Figure 8.4
  • SARSA Figure 13.5
    • with generalization Figure 13.7
    • with linear function approximation Figure 13.8
  • search
    • generic Figure 3.5
    • multiple-path pruning Figure 3.16
  • sigmoid (neural network) 9
  • stochastic policy iteration Figure 14.10
  • unification Figure 15.4
  • value iteration Figure 12.17
  • variable elimination
    • belief network Figure 9.13
    • CSP Figure 4.7
    • decision network Figure 12.14
    • single-stage decision network Figure 12.8
• algorithm portfolio §4.11, §4.6.2
• algorithms
  • bottom-up
    • conflict 1
    • definite clause 1
    • negation-as-failure 1
  • branch-and-bound 1
  • conflict
    • bottom-up 1
    • top-down 1
  • constraint satisfaction problem (CSP)
    • branch-and-bound 1
    • depth-first search 1
    • genetic algorithm 1
    • local search 1
    • variable elimination 1
  • Datalog
    • top-down proof procedure 1
  • decision network
    • depth-first search 1
    • variable elimination 1
      • single-stage 1
  • definite clause
    • bottom-up 1
    • top-down 1
  • depth-first
    • iterative deepening 1
  • domain splitting 1
  • generalized arc consistency 1
  • learner
    • k-means 1
    • boosting 1
    • decision tree 1
    • expectation maximization (EM) 1
    • gradient-boosted trees 1
    • logistic regression
      • stochastic gradient descent 1
    • neural network
      • Conv2D 1
      • dense linear function 1
      • dropout 1
      • ReLU 1
      • sigmoid 10
      • stochastic gradient descent 16
    • stochastic gradient descent
      • logistic regression 1
      • neural network 16
  • Markov decision process (MDP)
    • asynchronous value iteration 1
    • policy iteration 1
    • value iteration 1
  • multiple-path pruning 1
  • negation-as-failure
    • bottom-up 1
    • top-down 1
  • neural network
    • Conv2D 1
    • dropout 1
  • planning
    • as CSP §6.4
    • forward §6.2
    • partial-order 1
    • regression §6.3
  • probabilistic inference
    • depth-first 1
    • Gibbs sampling 1
    • likelihood weighting 1
    • MCMC 1
    • particle filtering 1
    • recursive conditioning 1
    • variable elimination 1
  • reinforcement learning
    • model-based 1
    • Q-learning 1
    • SARSA 1
      • with generalization 1
      • with linear function approximation 1
    • stochastic policy iteration 1
  • search
    • depth-first 1
    • game tree 1
    • iterative deepening 1
    • minimax with $\alpha$–$\beta$ pruning 1
  • stochastic gradient descent
    • logistic regression 1
    • neural network 16
  • top-down proof procedure
    • conflict 1
    • Datalog 1
    • definite clause 1
    • negation-as-failure 1
  • value iteration
    • asynchronous 1
• alignment problem §18.3
• Allais Paradox §12.1.1
• alpha–beta ($\alpha$–$\beta$) pruning §14.3.1
• AlphaGo §14.10
• AlphaZero §14.10, §14.7.3
• alternating least squares Example 17.3
• analysis 1st item
• Analytical Engine §1.2
• annealing §4.6.3
  • schedule §4.6.3
• answer §15.4.1, §5.3.1, §5.3.2, §5.6.2
  • clause §15.5.4, §5.3.2
  • extraction §15.4.1, §15.5.4
• any-conflict algorithm §4.6.3
• any-space algorithm 4th item
• anytime algorithm §1.5.4, §12.5.2, 1st item
• aperiodic Markov chain §9.6.1
• application of substitution §15.5.1
• applications of AI §1.1, §1.4
• approximate inference item Approximate inference, §9.7
• approximately optimal solution item Approximately optimal solution
• arc 2nd item
• arc consistent §4.3, §4.8.1
• area under the ROC curve §7.2.3
• argument 5th item, §5.7.1
• Aristotelian definition §16.2.2
• array §A.3
• Arrow’s impossibility theorem Proposition 14.1
• art §19.3
• artificial general intelligence §18.3, §19.2
• artificial intelligence §1.1
• Artificial Intelligence Act §18.8
• ask item Step 4, §5.3.1
• ask-the-user §5.4
• askable atom §5.4
• assertional knowledge base 2nd item
• assignment §4.1.1
• assisted action §18.3
• assisted cognition §18.3
• assisted perception §18.3
• assistive technology §18.3
• assumable §5.6.2, 2nd item
• assumption-based truth maintenance system §5.12, §5.6.4
• asymptotic complexity §1.6.2, §3.5.2
• asynchronous value iteration §12.5.2
  • algorithm Figure 12.18
• ATMS, see assumption-based truth maintenance system
• atom 5th item, §5.1.1, 1st item
• atomic
  • clause §15.9, 2nd item
  • proposition §5.1.1, 1st item
  • symbol 5th item
• atoms-to-bits §18.1, 2nd item
• attention
  • economy §18.1
  • human §18.1, §18.3
  • neural network 4th item, 5th item, §18.3, §8.5.4
  • to environment §12.5.5
• attribute §16.1.1
• auction §14.6
• AUROC, see area under the ROC curve
• autoencoder §8.6.1
• autoML §7.9, §8.3
• autonomous
  • agent §1.3, Chapter 18
  • delivery robot §1.4.1
  • vehicle §18.5, §2.4
• average reward item Average reward
• axiom item Step 4, item Step 3, §5.1.2
• axiomatizing the domain item Step 4, item Step 3
• axioms of rationality §12.1
• backdoor criterion §11.3.1
• backpropagation §8.1.1, §8.1.1
• backtracking §3.5.2
• backward induction §14.3
• backward search §3.8.1
• bag item Data, 3rd item
• bag-of-words §17.3.3, §9.6.6
• bagging 1st item
• bandit §13.5
• base learner 1st item
• base-level algorithms §7.5
• Basic Formal Ontology §16.6
• batch §7.3.2
• Bayes classifier §10.2.2
• Bayes’ rule §10.1, Proposition 9.1
• Bayesian
  • information criteria (BIC) §10.2.4, §10.3.1
  • learning §10.2
  • network, see belief network
  • probability §9.1
• beam search §4.7
• behavior §1.1
• belief §1.6.2, 6th item
  • monitoring §9.6.3
  • network §1.2, §10.4, §9.3, §9.3
  • state §1.3, §12.5.5, §2.1.2, §8.5.2
    • transition function 2nd item, §2.1.3, §2.2, §8.5.2, 2nd item
• Bell number §17.4
• best response §14.4
• best-first search §3.6
• beta distribution §10.2.1
• BFO, see Basic Formal Ontology
• bias
  • human §18.2
  • machine learning §18.2, item Bias, 1st item, §7.6, §8.1, 4th item
    • bias §10.1
  • representation 1st item
  • search 1st item
• bias–variance trade-off 2nd item
• bidirectional search §3.8.1
• bigram model §9.6.6
• binary
  • constraint §4.1.2
  • cross-entropy loss §7.2.1
  • log loss §7.2.1, 2nd item
  • variable §4.1.1, §9.1.1, §9.2
• binning 3rd item, §7.3.2
• binomial distribution §10.2.1
• biology item Biology, §8.5.4
• bipartite graph 3rd item
• bit §10.2.4, §7.2.1
• blame attribution problem 1st item
• blocks §11.1.2
• body
  • agent §2.1
  • clause 2nd item
• Boltzmann distribution 3rd item, §4.6.3, §4.7
• Boolean
  • feature §7.2
  • property §16.1.1
  • variable §4.1.1, 1st item, §9.1.1
• boosting §7.5.1
  • algorithm Figure 7.19
• bot §1.3, §2.1
• bottom $\perp$ 3rd item
• bottom-up proof procedure §5.3.2
  • assumables §5.6.4
  • Datalog §15.5.2
  • definite clauses Figure 5.3
  • negation as failure §5.7.2
• bounded above zero §3.6.1
• bounded arc costs §3.5.4
• bounded rationality 2nd item, §19.2
• branch-and-bound
  • factored optimization
    • algorithm Figure 4.12
• branch-and-bound search §3.6.2
  • factored optimization §4.8.1
• branching factor §3.3.1
• breadth-first search §3.5.1
• bucket elimination, see variable elimination
• burn-in §9.7.7
• canonical representation §12.1.2, §12.1.2, §15.8.1, §9.3.3, §9.3.3
• canyon §8.2
• cardinal item Optimal solution
  • preference 2nd item, §12.1.1
• case analysis §4.4
• catastrophic forgetting §13.9.1, §7.3.2
• categorical
  • cross entropy §7.2.1
  • feature §7.2.1
  • log loss §7.2.1, 3rd item
  • target §7.3.2
  • variable §10.2.1
• causal §2.1.1
  • link §6.5
  • mechanism §11.1, §5.9
  • model Chapter 11, §5.9
  • network §11.1, 2nd item
  • rule 1st item
• causality §1.2, Chapter 11, §5.9, §5.9
• chain rule 2nd item, §9.1.2
• chance node 2nd item
• channel 3rd item
• characteristic function item relations, §16.2
• CHAT-80 §1.2
• ChatGPT Example 1.2, §18.3
• checkers §1.2
• chess §14.10
• child §3.3.1
• choose 2nd item, §3.4, §5.3.2
• Church–Turing thesis §1.2
• Cicero §14.10
• citation matching §17.4
• clarity principle §4.1.1, 2nd item
• Clark normal form §15.9
• Clark’s completion §15.9, §5.7
• class §10.2.2, §16.2, 2nd item
• classification item Task, §7.2
  • tree §7.3.1
• clause 2nd item
  • definite 1st item, 2nd item
  • Horn §5.6.1
• climate change §18.6
• closed list, see explored set
• closed-world assumption §5.7
• clustering §10.3
• CNF, see conjunctive normal form
• CNN, see convolutional neural network
• cognitive science §1.2.1
• cold-start problem §17.2.1
• collaborative filtering §17.2.1
  • algorithm Figure 17.2
• collective classification §17.3.2
• collusion §17.3.2
• combinatorial auction §18.6
• command §13.4.1, §2.1, §2.1.3, §2.2
  • function 3rd item, §2.1.3, §2.2, §8.5.2
  • trace §2.1.1
• common sense §1.1.1, §18.3, §19.3
  • reasoning §1.6.3, Example 1.2
• competitive agents 2nd item
• compile §9.5.3
• complement (activation function) §8.1
• complements 1st item
• complete
  • algorithm §3.7.3, §4.6
  • bottom-up proof procedure item Completeness
  • knowledge assumption §5.7
  • proof procedure §5.3.2
• completeness of preferences Axiom 12.1
• complex preference 2nd item
• complexity §3.5.2
• compound proposition 2nd item
• compress §8.6.1
• computational
  • agent §1.1
  • limits dimension §1.5.4
  • linguistics §15.7
  • sustainability §18.6
• concept §16.3.1
• conceptualization §15.2, §16.3, item Step 2
• condition §4.1.2
• conditional
  • effect §6.1.2, §6.1.3
  • expected value §9.1.3
  • odds 2nd item
  • plan 3rd item
  • probability §9.1.2
  • probability distribution §9.1.2
  • probability table §9.3.3
• conditionally independent §9.2
• Condorcet paradox Example 14.17
• conflict §4.6.1, §5.6.2
• conflicting variable §4.6.3
• confounder §11.3
• conjugate prior §10.2.1
• conjunction 2nd item
• conjunctive normal form Example 5.22
• consequence set §5.3.2
• consistency-based diagnosis §5.6.3, §5.6.3
• consistent heuristic §3.7.2
• constant 2nd item
• constrained optimization problem §4.8
• constraint §18.6, §4.1.2
  • action §6.4.1
  • binary §4.1.2
  • effect 2nd item
  • frame 3rd item
  • goal §18.3, §18.6, 5th item
  • hard Chapter 4
  • initial-state 4th item
  • network §4.3
  • precondition 1st item
  • satisfaction §18.6, §4.1.3
  • soft §4.8
  • state 6th item
• constraint satisfaction problem (CSP) §4.1.3
  • branch-and-bound 1
  • depth-first search 1
  • domain splitting 1
    • algorithm Figure 4.6
  • generalized arc consistency 1
    • algorithm Figure 4.4
  • genetic algorithm 1
  • local search 1
  • planning §6.4
  • variable elimination 1
• context §8.5.1, §8.5.1
• context-free grammar §15.7.1
• context-specific independence §9.2, §9.3.3
• contingent attribute 2nd item
• continuant 2nd item
• continuous §2.3.1, §2.3.1, §4.8.3
  • time §9.6.5
  • variable §4.1.1
• continuous bag of words (CBOW) 1st item
• controller §14.2.1, §2.1, §2.1.1
  • model-based reinforcement learning Figure 13.6
  • Q-learning Figure 13.3
  • SARSA Figure 13.5
    • with generalization Figure 13.7
    • with linear function approximation Figure 13.8
  • stochastic policy iteration Figure 14.10
• Conv2D
  • class Figure 8.9
• convolution mask §8.4
• convolutional
  • model §17.3.4
  • neural network (CNN) §17.3.1, §8.4, §8.4, §8.4, §9.6.1
    • relational graph (R-GCN) §17.3.4
• cooperate §14.7.2
• cooperative agents 1st item
• cooperative games §14.10
• cooperative system Example 5.28
• coordinate §14.7.2
• coordination Example 14.12
• corner cases §18.3
• corpus §8.5
• cost §3.3.1, §4.8, §7.2.3
  • function §4.8
• counterfactual
  • explanation §11.6
• counterfactual reasoning §11.5
• CPT, see conditional probability table
• credit assignment problem 1st item
• cross entropy §7.2.1
• cross validation §7.4.3, §8.3
  • $k$-fold §7.4.3, §8.3
• crossover §4.7, §4.7
• crowd sourcing §17.3.2
• cryptocurrency §18.6
• CSP, see constraint satisfaction problem
• culture item Culture
• cumulative probability distribution §9.7.1
• cumulative reward §12.5
• curse of dimensionality item Curse of dimensionality
• cut 2nd item, §7.3.2
• cut-set §3.8.1
• Cyc §16.3
• cycle §3.3.1
  • pruning §3.7.1
• d-separated §11.1.2
• d-separation §11.1.2
• DAG (directed acyclic graph) §3.3.1
• data Chapter 10, Chapter 7, item Data
  • augmentation 2nd item
  • likelihood §10.1
  • lineage §16.4
  • provenance §16.4
  • relational Chapter 17
  • sequential §8.5
  • structure §15.6
• Datalog §15.4
• datatype property 3rd item
• DBN, see dynamic belief network
• DCG, see definite clause grammar
• dead reckoning §2.3.2
• death by GPS §3.9
• debugging
  • false negative §5.5.2
  • false positive §5.5.1
    • algorithm Figure 5.6
  • incorrect answers §5.5.1
  • missing answer §5.5.2, §5.5.2
    • algorithm Figure 5.7
• decision
  • function §12.3.2
  • Markov decision process §12.5
  • network §12.3.1, §12.3.1, 3rd item
    • dynamic §12.5.4
    • multiagent §14.2.3
    • single-stage §12.2.1
  • node 1st item
  • process §12.5
  • sequential §12.3, §12.3
  • single §12.2
  • variable §12.2
• decision tree §1.2, §12.2, 2nd item, §14.2.2, §7.3.1, §9.3.3
  • learning §10.2.3, §7.3.1
• decision tree learner
  • algorithm Figure 7.9
• decision-theoretic planning §1.2, §12.5.4
• decoder §8.5.1, §8.5.2
• deduction §5.3.2, §5.8
• deep §8.1
  • fake Chapter 18, §8.6.1, §8.6.2
  • learning §1.5.10, Chapter 8
  • reinforcement learning §13.9, 5th item
• Deep Blue §14.10
• Deep Space One §5.13
• default §5.7.1
• deficiency 2nd item
• definite clause 1st item, 2nd item
  • grammar (DCG) §15.7.1
  • resolution §5.3.2
• definitive prediction 1st item
• delay §15.8.2
• delivery robot §1.4.1
• dematerialization §18.1, §18.6, 2nd item
• DENDRAL §1.2
• denoise §8.6.3
• denote item Step 2, §15.3.1
• dense linear function §8.1.1
• dependent continuant 3rd item
• deployed cases are like training cases 4th item
• deployment §19.1, item Measuring success
• depth bound §3.5.3
• depth of neural network §8.1
• depth-bounded search §3.5.3
  • algorithm 12
• depth-first
  • branch-and-bound §3.6.2
    • algorithm Figure 3.14
  • CSP solver
    • algorithm Figure 4.1
  • decision network optimization
    • algorithm Figure 12.13
  • probabilistic inference
    • algorithm Figure 9.9
  • search §3.5.2
    • algorithm Figure 3.9
• derivation §15.5.4, §5.3.2, §5.3.2
• derivative §4.8.3
• derived §5.3.2
  • atom §5.9
  • feature §6.1.2
  • knowledge §16.2
• description logic §16.3.1
• descriptive theory §12.1.3
• design §1.1, §5.8
  • space §1.5
• design-time computation §1.5.9
• desire 6th item
• determinism 3rd item
• deterministic 1st item
  • planning 2nd item, Chapter 6
• dev (development) set §7.4.3
• diagnosis §5.8
  • abductive §5.8
  • consistency-based §5.6.3
  • decision-theoretic Example 12.9
• diagnostic assistant §1.4.2
• dictator §14.6
• dictionary §9.7.6
• difference list §15.7.1
• differentia 2nd item
• diffusion model §8.6.3
• Digital Services Act §18.8
• Dijkstra’s algorithm §3.11
• dimension §8.6.1
  • computational limits §1.5.4
  • effect uncertainty §1.5.6
  • interactivity §1.5.9
  • learning §1.5.5
  • modularity §1.5.1
  • number of agents §1.5.8
  • planning horizon §1.5.2
  • preference §1.5.7
  • representation §1.5.3
  • sensing uncertainty §1.5.6
• dimensionality reduction §8.6.1
• Diplomacy §14.10, §14.10
• direct cause §11.1
• directed acyclic graph §3.3.1
• directed graph §3.3.1
• Dirichlet distribution §10.2.1, 5th item
• discount §12.5
• discount factor item Discounted reward
• discounted reward item Discounted reward
• discrete
  • feature §2.3.1
  • optimization §4.8.1
  • time §2.1.1, §2.3.1, §9.6.4
  • variable §4.1.1, §9.1.1
• discretization §9.1.1, §9.6.5
• disintermediation §18.1, §18.4, 3rd item
• disjoint union §9.5.1
• disjunction 2nd item, §5.6.1
• disjunctive normal form Example 5.22
• distribution law §9.5
• distributional shift 5th item
• DNF, see disjunctive normal form
• do
  • calculus §11.3.2
  • command §13.4.1, §2.2
  • notation §11.1.1
• document §9.6.6
• domain item functions, 1st item, §16.1.1, §16.2.1, §4.1.1, §7.2, §9.1.1
  • consistent §4.3
  • ontology §16.3.1
  • splitting §4.4
• dominant strategy 1st item
• dominated strategy §14.4.1
• dominates §7.2.3
• don’t-care non-determinism 1st item
• don’t-know non-determinism 2nd item
• dot product §9.6.3
• down-sample 5th item
• DPLL algorithm §5.2.1
• dropout §8.3
  • class Figure 8.7
• DSA, see Digital Services Act
• dynamic
  • belief network §9.6.4
  • decision network §12.5.4, §12.5.4
• dynamic programming §1.2, §3.8.2, §8.1.1, §9.5.2
• dynamics §1.5.6, 3rd item, 5th item, 2nd item, 2nd item
• early stopping §7.4.3
• echo chambers §17.5
• ecological sustainability §18.6
• economically efficient mechanism 2nd item
• effect 2nd item, §6.1
  • constraint 2nd item
  • uncertainty dimension §1.5.6
• effectively computable function §1.2
• effector 2nd item
• elimination ordering §4.5
• EM, see expectation maximization
• embedding
  • item item Add $k$ latent properties
  • object 4th item
  • relation 5th item
  • subject 4th item
  • user item Add $k$ latent properties
  • word §8.5.1
• embodied §19.3
  • agent §1.2, §2.1
• empirical frequency §7.2.2
• empirical systems §1.1
• empty body 2nd item
• encoder §8.5.1, §8.5.2
• encoder–decoder recurrent neural network §8.5.2
• encoding §8.6.1
• endogenous variable §9.3.3
• engagement §17.5, §17.5
• engineering goal §1.1
• ensemble learning §7.5
• entails §5.1.2
• entity §1.5.3, 1st item, §16.3.2, Chapter 17
• entropy §7.2.1, §7.2.1, §7.3.1
• environment §1.3
• epistemology §1.2.1, §9.1
• epoch §7.3.2
• equality §15.8
  • uncertainty §17.4
• equilibrium distribution §9.6.1
• equivalence 2nd item
• ergodic Markov chain §9.6.1
• error item Measuring success
  • data item Imperfect data
  • debugging §5.5.1
  • false negative §5.5.2, §7.2.3
  • false positive §5.5.1, §7.2.3
• error function §4.8
• ethics §18.7
  • AI §18.7
  • consequentialist 2nd item
  • deontological 3rd item, §18.7
  • Kantian 3rd item
  • utilitarian 2nd item
  • virtue 1st item
  • washing §18.8
• Euclidean distance §3.7.2
• evaluate (learner) item Measuring success
• evaluation function §14.3.1, §4.6.1
• event 3rd item
• evidence Chapter 10, §9.1.2
• evidential model §5.9
• evolutionary algorithm §13.2, §13.9.2
• exact inference item Exact inference
• example Chapter 7
  • test item Measuring success
  • training item Task, item Measuring success, 3rd item
  • validation (dev) §7.4.3
• exchangeability §17.3.1
• exclusive-or 2nd item, Example 7.13
• existence 4th item
• existence uncertainty §17.4
• existentially quantified variable 2nd item, 2nd item
• exogenous variable §9.3.3
• expanding a path §3.4
• expectation 1st item
• expectation maximization (EM) §10.3.2, §10.4.1, §17.3.2
  • algorithm Figure 10.8
• expected
  • monetary value 2nd item
  • return of policy §12.5.1
  • sample size §10.5
  • utility §12.2
    • decision network §12.3.2
  • value §9.1.3
    • of policy §12.5.1
• experience §13.4
• expert §1.2
  • knowledge §10.2.1, 3rd item
  • system §1.2, §2.3.3
• explainability §18.3
• explainable AI §1.6.2, §18.3, §7.7
• explained away Example 5.32, Example 9.13
• explanation §11.6, §5.8
• exploit 1st item
• exploration §13.5
  • safe 4th item
• explore 2nd item
• explore–exploit dilemma 3rd item
• explored set §3.7.2
• exponentially-decaying rolling average §A.1
• extension §4.1.2
• extensional set §16.2
• extensive form of game §14.2.2, 4th item
• external knowledge source 3rd item
• external validity §7.7
• extrapolation item Interpolation and extrapolation
• $f(p)$ in $A^{\ast }$ §3.6.1
• facial
  • characterization 2nd item
  • detection 1st item
  • identification 4th item
  • recognition §18.2, §18.7, §18.8, §7.7
  • verification 3rd item
• fact 1st item, 2nd item
• factor §A.3, §9.3.3
  • graph §9.3.3
• factored finite state machine §2.1.3
• factored optimization problem §4.8
• factored representation §2.1.3
• factorization §9.3
• failure 2nd item, §5.7.2
  • natural §3.5.3
• fairness §1.6.1, §12.6, §15.6.1, §18.3, 1st item
• false §15.3.1, §5.1.2
• false-negative error item Probable solution, §5.5.2, §7.2.3
• false-positive error item Probable solution, §5.5.1, §5.5.1, §7.2.3
• false-positive rate 2nd item
• fault §5.6.3
• feasible §4.8
• feature §1.5.3, Chapter 4, §7.2
  • action §6.4.1
  • state §6.4.1
• feature engineering §13.9.1, §13.9.1, §7.3.2, Chapter 8
• feature selection §7.4.2
• feature-based representation of actions §6.1.3
• feedback item Feedback
• feedforward neural network §8.1
• fictitious play §14.7.2
• FIFO §3.5.1
• filter §8.4
• filter bubbles §17.5
• filtering 1st item, §9.6.2, §9.6.3
• finite failure §5.7.2
• finite horizon 2nd item
• finite state controller §2.1.3
• finite state machine §2.1.3
• first-order predicate calculus §15.6
• first-order weighted logical formula 2nd item
• fitness proportional selection 1st item
• fixed point item Fixed Point
• flat structure 1st item
• flatten 7th item
• floundering goal 2nd item
• flying machines §1.2.1
• fold 1st item
• for all ($\forall$) 1st item
• forward
  • chaining §5.3.2
  • planner §6.2
  • prediction §2.3.2
  • sampling §9.7.2
  • search §3.8.1
• found a solution §3.4
• foundation models §8.9
• frame
  • constraint 3rd item
  • rule 2nd item
• frames §1.2
• framing effect §12.1.1
• free parameters §9.2
• fringe §3.4
• front-door criterion §11.3.3
• frontier §3.4
• fully convolutional neural network 7th item
• fully expressive §17.2.2
• fully observable 1st item, §14.3
  • Markov decision process (MDP) 1st item
• function item functions
  • symbol §15.6
• functional gradient boosting §7.5.1
• functional property §16.2.1, 1st item
• fuzzy terms 2nd item
• gambling §9.1
• game
  • adversarial §14.3.1
  • decision network §14.2.3
  • extensive form §14.2.2
  • normal-form §14.2.1
  • tree §14.2.2
  • zero-sum 2nd item, §14.3.1
• game tree search 4th item
  • algorithm Figure 14.5
• GAN, see generative adversarial network
• GDPR, see General Data Protection Regulation
• General Data Protection Regulation §18.8
• general game playing §14.10
• generalization §16.2, item Measuring success
• generalized additive independence §12.1.2
• generalized answer clause §15.5.4
• generalized arc consistency (GAC) §4.3
• generate and test §4.2
• generative
  • adversarial network §1.2, §8.6.2
  • AI §1.2, §19.3, §8.6.3, 10th item
  • image model §8.6.1
  • language model §8.5.2, 3rd item, §9.6.6
• generic search algorithm §3.4
• genetic algorithm §4.7
  • algorithm Figure 4.11
  • crossover
    • algorithm 28
• genus 1st item
• Gibbard–Satterthwaite theorem §14.6
• Gibbs distribution 3rd item, §4.6.3, §4.7
• Gibbs sampling §9.7.7
  • algorithm Figure 9.35
• gig economy §18.4
• global optimum §4.6.1, §4.8.2
• global positioning system (GPS) §2.3.2, §9.8
• Glorot uniform initializer §8.2.4
• Go §14.10
• goal 4th item, 1st item, 6th item, 5th item, §3.3.1, §6.1.4, §6.2
  • constraint §18.3, §18.6, 5th item
  • node §3.3.1
  • state 5th item
• Google §17.3.3, §9.6.1, Example 9.38
  • translate §8.5.4
• governance §18.8
  • external §18.8
  • internal §18.8
• GPT §15.7.4
• GPT-3 Example 1.2, Figure 8.15, §8.5.5
• GPU §8.5.1
• gradient descent §4.8.3, §7.3.2
• gradient-boosted trees §1.2, §19.1, §7.5.2
  • algorithm Figure 7.21
• grammar §15.7.1
  • context-free §15.7.1
  • definite clause §15.7.1
• granularity §9.6.5
• graph §3.3.1
  • neural network §17.3.4
• graphical models §1.2, §9.3.3
• graphics processing units §8.5.1
• greedy 2nd item
  • ascent §4.6.1
  • best-first search §3.6
  • decoding §8.5.2
  • descent §4.6.1
  • optimal split §7.3.1
• green information technology §18.6
• ground expression §15.3
• ground instance §15.5.1, §15.5.2, §17.3.1
• ground truth §7.2.1, 1st item
• grounding §17.3.1
• guaranteed bounds 1st item
• $h(n)$, see heuristic function
• Hanabi §14.10
• hard clustering §10.3
• hard constraint Chapter 4, §4.1.2
• HCI §18.3
• head §16.1.3, 2nd item
  • transformer 1st item
• help system Example 10.5, Example 9.36
• Herbrand interpretation §15.5.2
• heuristic 1st item
  • depth-first search §3.6
  • function §3.6
  • knowledge §3.1
  • search §3.6
• hidden
  • Markov model (HMM) 2nd item, §9.6.2
  • property item Add a latent property
  • variable §10.3.2, §10.4.1, 3rd item
• hidden layer §8.1
• hierarchical
  • control 1st item, §19.2, §2.2
  • softmax §7.3.2
  • structure 3rd item
• high stakes 1st item
• hill climbing §4.6.1
• history 3rd item, §13.4, §2.1.1
• HMM, see hidden Markov model
• Hoeffding’s inequality §10.2.1, §9.7.1
• holdout §7.4.3
• horizon §1.5.2, §2.2, §6.4
• Horn clause §5.6.1
• human-centred AI §18.3
• human-compatible AI §18.3
• human-in-the-loop §1.1, §1.3, §18.3
• human–computer interaction §18.3
• hybrid system §2.3.1
• hyperbolic tangent 2nd item
• hyperparameter §7.4.2, §7.4.3
  • tuning §7.4.2, §7.9, §8.3
• hyperplane §7.3.2
• i.i.d., see independent and identically distributed
• identifiable §11.2
• identifier §16.1.2
• identity §15.8.1, 3rd item
  • uncertainty §17.4
• ImageNet §1.2
• immaterial entity 5th item
• imperfect data item Imperfect data
• imperfect information §12.4
  • game §14.2.2, §14.4
• implication 2nd item
• importance sampling §9.7.4, §9.7.5
• incoming arc §3.3.1
• inconsistent §5.6.1
• incorrect answer §5.5.1
• incremental gradient descent §7.3.2
• indefinite horizon 3rd item, §12.5
• independent and identically distributed (i.i.d.) §10.2
• independent continuant 3rd item
• independent variables §9.2
• indicator variable 1st item, 1st item, §7.3.2, §8.2.4, §8.5.1
• indifferent §12.1.1
• individual §1.5.3, 1st item, 1st item, 1st item, §4.7
• individual–property–value triple §16.1.1
• induction §5.8
• inductive bias item Bias
• inference §5.3.2
• infinite horizon 4th item, §12.5
• influence diagram §12.3.1
• information
  • content §7.2.1
  • gain §7.3.1
  • seeking actions §12.3
  • set §14.2.2
  • theory §10.2.4, §7.2.1
• inheritance §16.2.1
• initial part of a path §3.3.1
• initial-state constraint 4th item
• innate §1.2
• input
  • feature 1st item
  • layer §8.1
• insects 2nd item
• instance §15.4.1, §15.5.1, §15.5.1
  • ground §15.5.2
• instrumental variable §11.4
• insurance Example 12.1
• integrity constraint §5.6.1
• intelligence §1.1
  • augmentation §1.1
• intended interpretation §15.2, item Step 3, §16.3, item Step 2, §5.1.2
• intension §4.1.2, Example 4.7
• intensional set §16.2
• intention 6th item
• interactivity dimension §1.5.9, §19.2
• internal validity §7.7
• internationalized resource identifier §16.1.2, §16.3
• interpolation item Interpolation and extrapolation
• interpretability §18.3
• interpretation §15.3.1, §5.1.2
• intersection §A.4
• intervention Chapter 11, §5.9
• inverse graph 2nd item
• inverse reinforcement learning §19.3
• IRI, see internationalized resource identifier
• is_a Example 16.4
• island §3.8.1
• island-driven search §3.8.1
• item embedding item Add $k$ latent properties
• iterative best improvement §4.6.1
• iterative deepening §3.5.3
  • algorithm Figure 3.11
• iterative soft-thresholding §7.4.2
• Java §16.2.1
• join §A.4, §4.5
• joint probability distribution §9.1.1, §9.3
• $k$-fold cross validation §7.4.3, §8.3
• k-means §10.3.1
  • algorithm Figure 10.4
• Kaggle §7.9
• Keras §B.2, §8.1.1, §8.2.2, §8.2.3, §8.2.4, §8.9, Example 8.3
• kernel §8.4
  • function §7.5
  • one-dimensional §8.4
  • size §8.4
  • two-dimensional §8.4
• key embedding 2nd item
• keys
  • in attention §8.5.4
• knowledge §1.1.1, §1.6.2
  • base item Step 4, §5.1.2, 3rd item
    • designer §5.1.2
  • given 1st item
  • graph §16.1.3
  • learned 2nd item
  • level 1st item, §5.5
    • debugging §5.5
  • map 1st item
• knowledge graph §17.3.4
• $L0$ loss 1st item
• $L1$
  • loss 2nd item
  • regularizer §7.4.2
• $L2$
  • loss 3rd item
  • regularizer §7.4.2
• $L\mathrm{\infty }$ loss 4th item
• lambda calculus §1.2
• landmark 1st item
• language §15.7.1
  • model
    • definite clause §15.7
    • probabilistic §17.3.3, §9.6.6
  • natural §15.7, §9.6.6
• language model
  • large §8.5.5, §9.7.2
  • neural §8.5
• Laplace smoothing §10.2.1, §10.2.1, §7.4.1
• large language model §15.7.4, §18.2, §8.5.5, §9.7.2
• lasso §7.4.2
• latent
  • Dirichlet allocation (LDA) 4th item, §17.3.3
  • property item Add a latent property
  • tree model 3rd item
  • variable 3rd item, see hidden variable
• law of large numbers §9.7.1
• Laws of Robotics §18.7
• layer §8.1
• LDA, see latent Dirichlet allocation
• leaf §3.3.1
• learning §1.2, Chapter 10—§10.8, Chapter 13—§13.13, §17.2.1—§17.7, §2.3.3, Chapter 7—§7.10
  • as search item Learning as search
  • Bayesian §10.2
  • belief network §10.4—§10.4.4
  • bias §10.1, item Bias, 1st item
  • collaborative filtering §17.2.1
  • decision tree §10.2.3, §7.3.1
  • deep Chapter 8
  • dimension §1.5.5
  • expectation maximization (EM) §10.3.2, §10.4.1
  • k-means §10.3.1
  • minimum description length §10.2.4
  • missing data §10.4.2
  • multiagent §14.7.2
  • naive Bayes classifier §10.2.2
  • neural network Chapter 8
  • probabilistic classifier §10.2.2
  • probabilities §10.1
  • rate §7.3.2
  • reinforcement Chapter 13
  • relational Chapter 17
  • stochastic policies §14.7.2
  • structure §10.4.3
  • supervised item Feedback
  • to act Chapter 13
  • unsupervised §10.3, item Feedback
• least fixed point item Fixed Point
• least-cost search §3.5.4
• leave-one-out cross validation §7.4.3
• lethal autonomous weapon systems §18.10
• level of abstraction §1.6.4
• lifelong learning item Lifelong learning
• LIFO §3.5.2
• lifted inference §17.1
• lifted model §17.3.1
• LightGBM §B.1, §7.5.2, §7.9
• likelihood 1st item, §9.1.2
  • of data §10.1
  • ratio 2nd item
  • weighting §9.7.4
• likelihood weighting
  • algorithm Figure 9.33
• linear
  • classifier §7.3.2
  • function §7.3.2
  • programming §4.8
  • regression §13.9.1, §7.3.2
• linear rule for differentiation 1st item
• linearly separable §7.3.2
• linked data §16.6
• Linnaean taxonomy §16.2.2
• list Example 15.27
• literal 2nd item, §5.7
• liveness §1.6.1
• local optimum §4.6.1, §4.8.2
• local search §4.6, §4.6
  • algorithm Figure 4.8
• locality 1st item
• localization §9.6.2
• log loss §7.2.1, §7.3.2
  • binary §7.2.1
  • categorical §7.2.1
• log-likelihood 1st item
• log-linear model §9.3.3, §9.3.3
• logic §1.2
  • predicate §15.3
  • program §15.6
  • programming §5.12, §5.7
  • propositional §5.1
• Logic Theorist §1.2
• logical
  • connectives §5.1.1
  • consequence §15.3.2, §5.1.2
  • form §15.7.3
  • formula §15.3, §5.1.1
  • variable 1st item
• logically follows §5.1.2
• logistic
  • function §7.3.2
  • regression §1.2, §10.2.2, §7.3.2, §9.3.3
    • relational 2nd item
• logistic regression
  • algorithm Figure 7.12
• logit §9.3.3
• long short-term memory (LSTM) §8.5.3
• loop pruning §3.7.1
• loss item Measuring success, §7.2.1
  • 0–1 1st item
  • absolute 2nd item
  • sum squares 3rd item
  • worst case 4th item
• loss function §4.8
• lottery §12.1.1
• low stakes 1st item
• lowest-cost-first search §3.5.4, §3.5.4
• LSTM §8.5.3
• m-graph §11.2
• machine learning, see learning
• maintenance goal 1st item, 2nd item
• MAP model §10.1
• mapping item functions
• marginalizing §9.5, §9.5
• Markov
  • assumption §9.6.1
  • blanket §9.3, §9.7.7
  • chain §9.6.1
    • aperiodic §9.6.1
    • ergodic §9.6.1
    • periodic §9.6.1
  • chain Monte Carlo (MCMC) §17.3.2, §17.4, §9.7.7
  • decision process (MDP) §1.2, §12.5—§12.5.5, §13.1, 3rd item
    • fully observable 1st item
    • partially observable (POMDP) 2nd item
  • hidden Markov model (HMM) §9.6.2
  • logic network (MLN) §17.3.4
  • network §9.3.3
  • random field §9.3.3
• matched RNN §8.5.2
• material entity 5th item
• matrix §8.5.1
  • factorization item Add $k$ latent properties
  • multiplication item Add $k$ latent properties, §8.5.1, §8.5.1, §9.6.3
• max-pooling 6th item
• maximization 2nd item
• maximum a posteriori probability model §10.1
• maximum likelihood estimate §7.2.2
• maximum likelihood model §10.1
• MCMC, see Markov chain Monte Carlo
• MDL, see minimum description length
• MDP, see Markov decision process
• mean §7.2.2
  • loss §7.2.1
• mean log loss §7.2.1
• measure §9.1.1
• measure of improvement item Measure of improvement
• measurement model §12.6
• measuring success item Measuring success
• mechanism §14.1, §14.6
  • causal §11.1, §5.9
• mechanism design §14.6
• median §7.2.2
• mediating variable §11.3.3, §11.3.3
• memory §2.1.2, §8.5.2
• metadata §16.4
• MGU, see most general unifier
• micromobility §18.5
• min-factor elimination ordering 1st item
• mind map 1st item
• minibatch §7.3.2
• minimal
  • conflict §5.6.2
  • diagnosis §5.6.3
  • explanation §5.8
  • model §15.5.2, item Fixed Point
• minimax §14.3.1, §14.7.1
• minimax with $\alpha$–$\beta$ pruning
  • algorithm Figure 14.7
• minimum deficiency elimination ordering 2nd item
• minimum description length (MDL) §10.2.4
  • MDL principle §10.2.4
• misinformation §17.3.2
• missing at random (MAR) §11.2
• missing completely at random (MCAR) §11.2
• missing data §10.2.2, §10.4.2, item Imperfect data
• missingness graph §11.2
• MLN, see Markov logic network
• MNIST Example 8.3
• mode §10.2.1, §7.2.2
• model §1.6.4, §5.1.2, item Representation, §7.1
  • complexity §7.4
  • MAP §10.1
  • maximum likelihood §10.1
• model averaging §10.2
• model-based reinforcement learning
  • algorithm Figure 13.6
• modified policy iteration §12.5.3
• modular
  • structure 2nd item
• modularity §1.5.1, §1.5.1
• modus ponens §5.3.2
• momentum Table B.2, §8.2.1
• money pump §12.1.1
• monitoring §9.6.2, §9.6.3
• monotone restriction §3.7.2
• monotonic logic §5.7.1
• Monte Carlo
  • Markov chain §9.7.7
  • sequential §9.7.6
  • tree search (MCTS) 2nd item, §9.7.2
• moral §18.7
  • agent §18.7
  • machines §2.4
  • patient §18.7
• most general unifier §15.5.1, §15.5.3
• most improving step §4.6.3
• multi-armed bandit §13.5
• multi-head attention 1st item
• multi-task learning 4th item
• multiagent decision network §14.2.3
• multiagent reasoning 3rd item, Chapter 14—§14.11
• multinomial
  • distribution §10.2.1
  • logistic regression §7.3.2
  • logit §7.3.2
• multiple-path pruning §3.7.2, §3.7.2
• multiset item Data
• mutex constraint §6.4.1
• MYCIN §1.2
• myopic 2nd item
• n-gram §9.6.6
• naive baseline §7.2.2
• naive Bayes classifier §10.2.2, §10.3.2, Example 9.36
• Nash equilibrium §14.4
• natural kind §10.2.2, §16.2
• natural language processing §15.7, §9.6.6
• nature §1.3, 1st item, §14.1
• negation 2nd item, §5.6.1
• negation as failure §15.9, §15.9, §5.7, §5.7.2
• negatively 2nd item
• neighbor §3.3.1
• Netflix Prize §17.2.1
• neural
  • network §1.2
    • graph §17.3.4
    • relational graph convolutional §17.3.4
• neural language model §8.5
• neural network §11.6, Chapter 8—§8.10
  • convolutional (CNN) §8.4
  • dense linear function
    • class Figure 8.3
  • recurrent §8.5.2
  • stochastic gradient descent
    • algorithm 15
• neural networks Chapter 8
• neuro-symbolic AI Chapter 17
• neuroevolution §13.12, §13.2
• neuron §1.2, Chapter 8
• no answer §5.3.1
• no-forgetting
  • agent §12.3.1
  • decision network §12.3.1
• no-free-lunch theorem §18.2, §7.6
• node 1st item
• noise item Imperfect data, 3rd item
  • variable Example 17.10, §9.3.3, §9.3.3
• noisy observation §9.6.2
• noisy-or 1st item, Example 17.10, §9.3.3, §9.3.3, Example 9.38
• non-cooperative games §14.10
• non-deterministic choice §3.4
• non-deterministic procedure 2nd item
• non-monotonic logic §5.7.1
• non-planning agent 1st item
• non-serial dynamic programming §4.11
• non-terminal symbol §15.7.1
• nonlinear function §8.1
• nonlinear planning §6.5
• nonparametric distribution §9.1.1
• normal-form game §14.2.1
• normalize §8.2.4
• normative theory §12.1.3
• noun 2nd item
• $NP$ 2nd item
• $NP$-complete 2nd item
• $NP$-hard 2nd item
• $\mathrm{\#}NP$ (sharp-NP) §9.4
• number of agents dimension §1.5.8
• number uncertainty §17.4
• NumPy §8.5.1
• object §1.5.3, 1st item, 3rd item, §16.1.1, §16.3.2
  • embedding 4th item
  • property 3rd item
• object-oriented languages §16.2.1
• objective function 2nd item
• observation 2nd item, §5.4, §9.1.2
• occurrent 2nd item
• occurs check §15.6.1
• Ockham’s razor §7.4.2, §7.6
• odds 2nd item
• off-policy learner §13.7
• offline 1st item
  • computation §2.3.3
  • learning item Online and offline
  • reasoning 1st item
• offspring §4.7
• omniscient agent §4.1.1
• on-policy learner §13.7
• one-dimensional kernel §8.4
• one-hot encoding §7.3.2, §8.1, §8.2.4, §8.5.1
• one-point crossover §4.7
• online 2nd item
  • computation 2nd item, §2.3.3
  • gradient descent §7.3.2
  • learning item Online and offline
• ontology §16.3, 3rd item, §5.4, §9.1
• open §15.3.2
• open-world assumption §5.7
• optimal
  • policy
    • decision network §12.2.1, §12.3.2
    • MDP §12.5.1
    • search §3.8.2
  • single decision §12.2
  • solution item Optimal solution, §3.3.1, §3.5.4
• optimal solution item Optimal solution, §3.2
• optimality criterion 3rd item
• optimism in the face of uncertainty 1st item
• optimization problem §4.8
  • constrained §4.8
  • factored §4.8
• oracle 2nd item, 2nd item
• orders of magnitude reasoning 2nd item
• ordinal item Optimal solution
  • feature 2nd item, §7.3.2
  • preference 2nd item, §12.1.1
• organizations §1.1.2
• outcome §12.1.1, §12.2, §14.2.1
• outgoing arc §3.3.1
• outlier Example 7.3
• output Chapter 7
• output layer §8.1
• over-parametrized §7.3.2
• overconfidence §7.4
• overfitting §10.1, Example 10.1, §7.4
• overflow §7.3.2
• OWL §16.3, §16.3.1, §16.3.1
• PAC, see probably approximately correct
• padding 2nd item
• PageRank §9.6.1
• pair item tuples
• parameter sharing §17.3.1, 2nd item, §8.5.2, §9.6.1
• parameterized random variable §17.3.1
• parametric distribution §9.1.1
• paramodulation §15.8.1
• parent
  • belief network §9.3
  • graph §3.3.1
• partial derivative §4.8.3
• partial observation §9.6.2
• partial restart §4.6.5
• partial-order planner
  • algorithm Figure 6.6
• partial-order planning §6.5
• partially observable 2nd item, §12.5.5
  • game §14.2.2, §14.4
  • Markov decision process 2nd item, §12.5.5
• particle §9.7.6
• particle filtering §9.7.6
  • algorithm Figure 9.34
• partition function §10.1, §9.3.3
• passive sensor 2nd item
• past experience 3rd item
• path §3.3.1
  • consistency §4.3
• pattern database §3.6.3, §3.8.2
• payoff matrix Example 14.1
• percept §13.4.1, §2.1
  • function §2.2
  • stream §2.1.1
  • trace §2.1.1
• perceptron §1.2
• perdurant 2nd item
• perfect information §14.3
• perfect rationality 1st item
• perfect-information game §14.2.2, §14.7.1
• periodic Markov chain §9.6.1
• personalized recommendations §17.2.1, §17.2.1
• philosophy §1.2.1
• physical symbol system §1.6.4
  • hypothesis §1.6.4
• piecewise constant function §7.5
• piecewise linear function §7.5
• pixel §2.1
• plan §6.2
• planner §6.2
• planning §1.2, §6.2—§6.9
  • CSP §6.4
  • deterministic Chapter 6
  • forward §6.2
  • horizon §1.5.2, §12.5, §2.2
    • dimension §1.5.2
  • partial-order §6.5
  • regression §6.3
• plate §17.3.1
  • model §17.3.1
• Pluribus §14.10
• point estimate §7.2.1, 3rd item
  • categorical §7.2.1
• poker §14.10
• policy §12.2.1, §3.8.2
  • decision network §12.3.2
  • MDP §12.5.1
  • POMDP 3rd item
  • stochastic §14.7.2
• policy iteration §12.5.3
  • algorithm Figure 12.19
  • stochastic 1
• policy search §13.2
• polyadic decomposition §17.2.2
  • with inverses §17.2.2
• POMDP, see partially observable Markov decision process
• pooling 6th item
• population Chapter 17, §4.7, §9.7.6
• portfolio §4.6.2
• positional encoding 3rd item
• positively 2nd item
• possible action 1st item
• possible world §12.2, §12.3.2, §9.1.1
• posterior distribution §9.3.1, §9.4
• posterior probability §9.1, §9.1.2, §9.1.2
• pragmatics item Pragmatics
• precision §7.2.3
• precondition 1st item, §6.1, §6.1.2
• precondition constraint 1st item
• predicate
  • calculus §15.3
  • logic §15.3
  • symbol 3rd item
• predictive policing §7.7
• predictor §7.2, §7.2.1, §7.3
• preference 4th item, §12.1.1, §4.8
  • bias item Representation
  • dimension §1.5.7
  • elicitation §12.1.2, §19.3
  • relation §12.1.1
• preposition 3rd item
• primitive
  • atom §5.9
  • feature §6.1.2
  • knowledge §16.2
  • proposition §9.1.1
  • relation 3rd item
• prior §7.4.1
  • count §7.4.1
  • knowledge 1st item
  • odds 2nd item
  • probability §10.1, §9.1, §9.1.2, §9.1.2
• prisoner’s dilemma §14.4
• privacy §17.2.1
• privacy-by-design §18.7
• probabilistic
  • bounds 2nd item
  • causal model §11.1
  • circuit §9.5.3
  • independence §9.2
  • inference §9.4, §9.5
  • language model §17.3.3, §9.6.6
  • logic model §17.3.1
  • logic program 1st item, §17.3.4, §9.3.3
  • logic programming 1st item
  • prediction 2nd item
  • programming 1st item, §9.3.3
  • relational model, see relational probabilistic model
  • soft logic (PSL) §17.3.4
• probabilistically
  • depends on §9.3
• probability §9.1—§9.11
  • Bayes’ rule §10.1, Proposition 9.1
  • conditional §9.1.2
  • density function §9.1.1
  • distribution §9.1.1
  • measure §9.1.1
  • posterior §9.1.2
  • prior §9.1.2
  • semantics §9.1.1
• probable solution item Probable solution, item Probable solution
• probably approximately correct (PAC) §1.6.3, §10.2.1, §9.7.1
• process 4th item, 3rd item
• project §A.4, §4.5
• Prolog §1.2, §15.3, §5.3.2
• proof §5.3.2
  • predicate calculus §15.5
  • procedure §5.3.2
    • bottom-up §15.5.2, §5.3.2
    • conflict Figure 5.10
    • Datalog §15.5.2, §15.5.4
    • negation-as-failure §5.7.2
    • top-down §15.5.4, §5.3.2
• proof procedure
  • conflict
    • bottom-up
      • algorithm Figure 5.9
    • top-down
      • algorithm Figure 5.10
  • Datalog
    • top-down
      • algorithm Figure 15.5
  • definite clause
    • bottom-up
      • algorithm Figure 5.3
    • top-down
      • algorithm Figure 5.4
  • negation-as-failure
    • bottom-up
      • algorithm Figure 5.11
    • top-down
      • algorithm Figure 5.12
• $prop$ Example 16.3
• property §1.5.3, §16.1.1, §16.1.1, 3rd item, Chapter 17
  • inheritance §16.2.1
• proposal distribution §9.7.5
• proposition §1.5.3, 2nd item, Chapter 5, §5.1.1, §5.1.1
• propositional
  • constraint §5.2
  • definite clause §5.3
    • resolution §5.3.2
  • satisfiability §5.2
• prospect theory §12.1.1, §12.1.3
• Protégé §16.3.1
• protein folding §8.5.4, §8.7
• proved §5.3.2
• provenance §16.4
• pruning belief network §9.5.3
• pseudo-examples §7.4.1
• pseudocount §10.2.1, §10.2.2, §7.4.1
• psychology §1.2.1
• punishment §12.5
• pure literal §5.2.1
• pure strategy §14.4
• purposive agent §1.3, §2.1
• Python §16.2.1
• PyTorch §B.2, §8.1.1
• Q function
  • $Q^{\pi }$ 2nd item
  • $Q^{\ast }$ §12.5.1, §13.4.1
  • Q-value 2nd item
• Q-learning §1.2, §13.4.1, 5th item
  • algorithm Figure 13.3
• qualitative
  • derivatives 3rd item
  • reasoning §2.3.1
• quality-adjusted life year (QALY) §12.6
• quantitative reasoning §2.3.1
• query
  • (Datalog) §15.4.1
  • (logic) §5.3.1
  • in attention §8.5.4
  • variable (belief network) §9.3.1
• query embedding 1st item
• querying the user §5.4
• queue §3.5.1
• random
  • forest §7.5
  • initialization §4.6
  • restart §10.3.1, 1st item, §4.6, §4.6.5
  • sampling §4.6
  • step 2nd item
  • variable §9.1.1
  • walk §4.6
• randomized clinical trial §11.6
• randomized controlled trial §11.3
• range item functions, §16.1.1, §16.2.1
• ranking §17.2.1
• rational §12.1.1
• rational agent §12.1
• RDF §16.3
• RDFS (RDF schema) §16.3
• reactive system §2.3.2
• reasoning Chapter 9
• reasoning with uncertainty Chapter 9
• recall 1st item
• receiver operating characteristic space §7.2.3
• recognition §5.8
• recommender system §17.2.1
• record linkage §17.4
• recoverable §11.2
• rectified linear unit §7.3.2, §8.1
• recurrent neural network (RNN) §8.5.2, §9.6.3
• recursive conditioning
  • algorithm Figure 9.12
• reference point §12.1.3
• regression item Task, §7.2
  • linear §7.3.2
  • logistic §7.3.2
  • planning §6.3, §6.3
  • to the mean §7.4
  • tree §7.3.1, §7.5
• regularization item Regularize, §7.4.2
• regularization parameter §7.4.2
• regularizer §7.4.2
• regulatory capture §18.8
• reify §16.1.1
• reinforcement learning §1.2, Chapter 13—§13.13, item Feedback
  • from human feedback §18.3
• rejection sampling §9.7.3
• relation item relations, §A.4, §1.5.3, 2nd item, Chapter 17, Chapter 17
  • embedding 5th item
• relation scheme §A.4
• relational
  • algebra §A.4
  • data Chapter 17
  • database §A.4
  • dependency network §17.3.4
  • graph convolutional network (R-GCN) §17.3.4
  • learning Chapter 17, §7.2
  • logistic regression 2nd item, §17.3.4
  • probabilistic model §17.3.1, §17.3.1
  • representations 3rd item
  • uncertainty §17.3.1, §17.4
• ReLU §7.3.2, §8.1
• ReLU (neural network)
  • class Figure 8.4
• remember §2.1.3, §2.2
• renaming §15.5.1
• Rephil §17.3.3, Example 9.38
• representation §1.6.2, §1.6.4, §8.6.1
  • bias item Representation, 1st item
  • dimension §1.5.3, §1.5.3
  • learning §7.3.2
• representation learning Chapter 8
• resampling §9.7.6
• residual network 8th item
• resilience §18.6
• resolution §5.3.2, §5.3.2
  • SLD §15.5.4, §5.3.2
• resolvent §5.3.2
• resource §16.1.2, §16.3
  • description framework (RDF) §16.3
  • goal 4th item
• retry 2nd item
• return §12.5, §13.4.1
• revelation principle §14.6
• reward 6th item, §12.5, §12.5, item Measuring success
  • average item Average reward
  • discounted item Discounted reward
  • engineering §12.6
  • function 4th item
  • hacking 2nd item
  • total item Total reward
• rewrite rule §15.7.1, §15.8.1
• ridge regression §7.4.2
• risk averse §12.1.1
• RL, see reinforcement learning
• RLHF, see Reinforcement Learning from Human Feedback
• RMS-Prop Table B.2, §8.2.2
• RNN, see recurrent neural network
• RoboCup §18.6
• robot §1.3, §1.4.1, §2.1
  • scientist §15.10
• ROC space §7.2.3
• rolling average §A.1
• root §3.3.1
• root-mean-square (RMS) error 3rd item
• RPM, see relational probabilistic model
• rule 1st item, 2nd item
• rule of inference §5.3.2
• run §14.2.2
• run-time distribution §4.6.4
• saddle point §8.2
• safe exploration 4th item
• safety §1.6.1, §18.3, §18.3, §18.3, §18.5, §18.8
• safety goal 2nd item
• salience §18.3
• sample Chapter 7
• sample average §9.7.1
• SARSA §13.7
  • algorithm Figure 13.5
  • with generalization
    • algorithm Figure 13.7
  • with linear function approximation §13.9.1
    • algorithm Figure 13.8
• SAT §5.2
• satisfiable §5.8
• satisficing solution item Satisficing solution, §3.1
• satisfy
  • constraint §4.1.2
  • policy §12.3.2
• scalable oversight 3rd item
• scenario §5.8
• schema (Kant) §1.2
• scheme
  • relation §A.4
• scientific goal §1.1
• scope §A.3, §A.4, 1st item, §4.1.2, §4.8, §9.3.3
• SDG, see Sustainable Development Goals
• search 2nd item, Chapter 3—§3.12
  • $A^{\ast }$ §3.6.1
  • bias item Learning as search, 1st item
  • bidirectional §3.8.1
  • breadth-first §3.5.1
  • cycle-pruning §3.7.1
  • depth-first §3.5.2
  • domain splitting §4.4
  • dynamic programming §3.8.2
  • for CSPs §4.2
  • generic
    • algorithm Figure 3.5
  • gradient descent §4.8.3
  • greedy best-first §3.6
  • heuristic §3.6
  • island driven §3.8.1
  • iterative deepening §3.5.3
  • local search §4.6
  • lowest-cost-first §3.5.4
  • minimax §14.3.1
  • multiple-path pruning
    • algorithm Figure 3.16
  • policy §13.2
  • stochastic local §4.6.2
• search and score §10.4.3
• search strategy §3.5
• second-order logic §15.6
• second-price auction §14.6
• select §3.4, §5.3.2
• selection §A.4
• self-attention §8.5.4
• self-driving cars §2.4
• semantic interoperability 3rd item
• semantic network §16.1.3
• semantic roles Example 16.5
• semantic web §16.3
• semantics Figure 15.1, §5.1.2
  • natural language item Semantics
  • predicate calculus §15.3.1
  • propositional calculus §5.1.2
  • variables §15.3.2
• semi-autonomous §18.3, §18.3
  • agent §1.3, Chapter 18, §18.3
• semi-decidable logic §15.6
• semi-supervised learning §8.6.1
• sensing uncertainty dimension §1.5.6, §19.2
• sensor 1st item, 2nd item
• sensor fusion Example 9.33
• sentence §15.7.1, §9.6.6
• separable control problem §2.3.2
• sequence-to-sequence mapping §8.5.2
• sequential
  • decision problem §12.3
  • Monte Carlo §9.7.6
  • prisoner’s dilemma §14.4
  • probability model §9.6
• sequential data §8.5
• set item sets
  • -of-words model §17.3.3, §9.6.6
  • difference §A.4
• SGD, see stochastic gradient descent
• shortcut connection 8th item
• SHRDLU §1.2
• side-effect 1st item
• sigmoid (neural network)
  • class 9
• sigmoid function §7.3.2, 2nd item, 1st item
• Simpson’s paradox §11.3.4
• simulated annealing §4.6.3, §4.6.3
• simultaneous localization and mapping (SLAM) §9.8
• simultaneous-action games §14.2.2
• single agent 1st item
• single decision §12.2
• single-stage decision network §12.2.1
• singularity §18.3, §19.3
• situated agent §1.2
• skip connection 8th item
• Skip-gram model 2nd item
• SLD derivation §15.5.4, §5.3.2
• SLD resolution §15.5.4, §5.3.2
• Smalltalk §16.2.1
• smart home §1.4.5
• SMC, see sequential Monte Carlo
• smooth §4.8.3
• smoothing §9.6.2, §9.6.3
• Sobel–Feldman operator Example 8.8
• social preference function §14.5
• society §1.1.2
• soft clustering §10.3
• soft constraint Chapter 4, §4.8
• softmax 3rd item, §7.3.2, 3rd item
  • hierarchical §7.3.2
• softmax regression §7.3.2
• software agent §1.3
• software engineering §1.6.3
• solution §3.2, §3.3.1, §4.1.3
• sound §5.3.2
• spam filter §10.5
• squared loss §10.3.1, 3rd item, 1st item
• squashed linear function §7.3.2
• stable assignment §10.3.1
• stack §3.5.2
• Stackelberg security games §14.8, §18.6
• stage §1.5.2, §9.6.1
• stakes 1st item
• start node §3.3.1
• start state 2nd item
• starvation §15.6.1, 1st item
• state §1.5.3, §3.2, §9.6.1
  • -space search problem §3.2
  • constraint 6th item
  • feature §6.4.1
  • space §3.2
  • space graph §3.3.1, §6.1.1, §6.2
  • variable 1st item
• stationary
  • distribution §9.6.1, §9.7.7
  • model §12.5, 3rd item, §9.6.1
  • policy §12.5.1
• statistical relational AI §1.2, Chapter 17, §17.3.1
• statistics §1.2
• step size §4.8.3, §4.8.3
• stimuli 2nd item, §2.1
• stochastic
  • beam search §4.7
  • dynamics 2nd item
  • gradient descent (SGD) §7.3.2
  • input §9.3.3
  • local search §4.6.2
  • policy §14.7.2, §14.7.2
  • policy iteration §14.7.2, 6th item
  • simulation §9.7
  • strategy §14.4
• stochastic gradient descent §8.1.1
• stochastic policy iteration
  • algorithm Figure 14.10
• stopping state §12.5
• strategic agent §14.1
• strategic-form game §14.2.1
• strategy §14.2.1, §14.2.2, §14.4
  • profile §14.2.2, §14.4
• strictly dominated §14.4.1, §4.8.1
• strictly preferred §12.1.1
• stride 5th item
• STRIPS assumption §6.1.2
• STRIPS representation §6.1.2, §6.1.2
• structural causal model §11.1, §5.9
• structure learning §10.4.3
• structured prediction item Task, §7.2
• STUDENT §1.2
• sub-property §16.2.1
• subclass §16.2.1
• subgame-perfect equilibrium §14.4
• subgoal §5.3.2, §5.3.2, 1st item, §6.3
• subject 3rd item, §16.1.1
  • embedding 4th item
• subjective probability §9.1
• substitutes 2nd item
• substitution §15.5.1
• successor §4.6
• sufficient statistics §10.3.1, §10.3.2
• sum of losses §7.2.1
• superintelligence §18.3
• supervised learning §10.4, item Task, item Feedback, §7.10, §7.2—§7.2
• support set item 2, §14.4
• surveillance capitalism §18.1, §18.8
• sustainability §18.6
• sustainable development §18.6
• Sustainable Development Goals §18.6
• symbol §1.6.4, §15.3, §4.1.1
  • level 2nd item
  • system §1.6.4
• symptoms §1.4.2
• syntax
  • natural language item Syntax
  • predicate calculus §15.3
  • propositional calculus §5.1.1
  • propositional definite clauses §5.3
• synthesis §1.1
• systems 1 and 2 §2.2, §2.6
• tabu search §4.6.3
• tabu tenure §4.6.3
• tail §16.1.3
• tangent §4.8.3
• tanh 2nd item
• target Chapter 7
• target features 2nd item
• task item Task, item Task
• TBox 1st item
• TD error §13.3
• tell §2.2, item Step 3
• temperature 3rd item
• temporal difference
  • equation §13.3
  • error §13.3
• temporal-difference learning §1.2
• tensor §8.5.1
• tensorflow §B.2
• term 4th item, §15.6
• terminal symbol §15.7.1
• terminological knowledge base 1st item
• test example item Measuring success
• thematic relations Example 16.5
• theorem §5.3.2
• Theorist §5.12
• there exists ($\exists$) 2nd item
• thing §1.5.3, 1st item, §16.3.2
• Thompson sampling 5th item
• thought §1.1
• threat Example 14.14
• time §2.1.1
• time granularity §9.6.5
• time-homogenous model §9.6.1
• tit-for-tat §14.4
• TMS, see truth maintenance system
• token §15.7.1, §8.5
• tokenization §8.5
• top-down proof procedure §15.5.4, §5.3.2
• top-level ontology §16.3.2
• top-n §17.2.1, §17.2.1
• topic model §17.3.3, §9.6.6
• total assignment §4.1.1
• total reward item Total reward
• tournament selection §4.7
• tractable §1.6.2
• trading agent §1.4.4
• tragedy of the commons §14.10, §14.8, §18.6
• training example item Task, item Measuring success, 3rd item
• transduction §2.1.1
• transfer learning §19.3
• transformer §1.2, §9.6.6
• transformers §8.5.4
• transient goal 3rd item
• transitivity of preferences Axiom 12.2
• transparency §18.3
• tree §3.3.1
• tree-augmented naive Bayes (TAN) network 2nd item
• treewidth §4.5, §9.5.3
• triangle inequality §3.7.2
• trigram §9.6.6
• triple item tuples, §16.1.1
• triple representation §16.1.1
• triple store 3rd item
• trolley problem §2.4
• trolley problems §12.1.3
• true item relations, §15.3.1, §5.1.2
• true-positive rate 1st item
• trust §18.7
• trustworthiness §18.3
• truth discovery §17.3.2
• truth maintenance system §5.12
• truthful 1st item
• try (local search) §4.6
• tuple item tuples, §A.4
• Turing machine §1.2
• Turing test §1.1.1
• tutoring Example 1.7
• tutoring agent §1.4.3, Example 1.10, Example 1.17, Example 1.22, Example 1.28, Example 1.33, Example 3.5, §5.8, §5.8
• two-dimensional kernel §8.4
• two-player zero-sum game 2nd item
• two-stage choice §4.6.3
• two-step belief network §9.6.4
• $type$ Example 16.4
• type I error §7.2.3
• type II error §7.2.3
• types of data 5th item
• UCB1 4th item
• UML 6th item
• unary constraint §4.1.2
• unary relations 2nd item
• unconditionally independent §9.2
• underflow §7.3.2
• undirected model §9.3.3
• unfolded network §12.5.4, §9.6.4
• unification §15.5.3, §15.5.3
  • algorithm Figure 15.4
• unifier §15.5.1
• uniform resource identifier §16.1.2
• uniform-cost search §3.5.4
• unify §15.5.1
• unigram §17.3.3, §9.6.6
• uninformed search strategy §3.5, §3.6
• union §A.4
• unique names assumption (UNA) §15.8.2
• unit (neural network) Chapter 8, §8.1
• unit resolution 2nd item
• universal basic income §18.4
• universal function approximator §19.3
• universally quantified variable 1st item, 1st item
• unnormalized probabilities 3rd item
• unsatisfiable §5.6.1
• unstructured 5th item
• unsupervised learning §10.3, §10.3.2, item Feedback
• upper confidence bound 4th item
• URI, see uniform resource identifier
• useful action 2nd item
• user 1st item, §4.1.1, §5.4
• user embedding item Add $k$ latent properties
• utility item Optimal solution, Proposition 12.3, 2nd item, item Measuring success
  • engineering §12.6
• utility node 3rd item
• $V^{\pi }$ 1st item, §12.5.1
• $V^{\ast }$ §12.5.1
• validation set §7.4.3
• value §12.5
  • decision network §12.2.1
  • in attention §8.5.4
  • iteration §12.5.2
  • of control §12.4
  • of information §12.4
• value embedding 3rd item
• value iteration
  • algorithm Figure 12.17
• variable Chapter 4, §4.1.1
  • action 2nd item
  • algebraic §4.1.1
  • assignment §15.3.2
  • binary §4.1.1, §9.1.1
  • Boolean §4.1.1, 1st item, §9.1.1
  • continuous §4.1.1
  • decision §12.2
  • discrete §4.1.1, §9.1.1
  • existentially quantified 2nd item
  • logical 1st item
  • random §9.1.1
  • state 1st item
  • universally quantified 1st item
• variable elimination §4.5, §9.5.2
  • belief network §9.10, §9.5.2
    • algorithm Figure 9.13
  • CSP §4.5
    • algorithm Figure 4.7
  • decision network §12.3.4
    • algorithm Figure 12.14
  • single-stage decision network §12.2.1
    • algorithm Figure 12.8
  • soft constraints §4.8.1
• variance 2nd item
• variational inference 3rd item
• VCG (Vickrey–Clarke–Groves) mechanism §14.6
• VE, see variable elimination
• vector §8.1, §8.5.1
• verb 3rd item, §16.1.1
• vigilance §18.3
• violates §4.1.2
• virtual body §2.2
• vocabulary §8.5
• walk §4.6
• Watson §1.2, §15.10
• weak learner §7.5.1
• weakly dominated §4.8.1
• weakly preferred §12.1.1
• web ontology language, see OWL
• web services §1.4.4
• weight §7.3.2
• weight tying §17.3.1, 2nd item, §9.6.1
• weighted logical formula §9.3.3
  • first-order 2nd item
• weighted model counting §9.3.3
• width (neural network) §8.1
• Wikidata §16.1.2, §16.6, Example 16.7
• winner-take-all §18.1
• Winograd schema §1.1.1
• word §15.7.1, §8.5, §9.6.6
• word embedding item Add $k$ latent properties, §8.5.1, §8.5.1, §8.5.1
• Word2vec §8.5.1, §8.9
• world §1.3
  • possible §12.2, §9.1.1
• worst-case loss 4th item
• wrapper 3rd item
• XGBoost §B.1, §7.5.2, §7.9
• XML §16.3
• YAGO §16.6
• yes answer §5.3.1
• Zeno’s paradox §3.5.4
• zero padding 2nd item
• zero-sum game 2nd item, §14.3.1
• zero–one loss 1st item
• $ϵ$-greedy exploration strategy 2nd item
• $\pi$ (denotation of predicate symbols) 3rd item
• $\pi$ (meaning of atoms) §5.1.2
• $\varphi$ (denotation of terms) 2nd item, §15.6