Artificial Intelligence: Foundations of Computational Agents, 2nd Edition 11.9 Exercises 12.1 Reinforcement Learning Problem

Chapter 12 Learning to Act

Since in action it frequently happens that no delay is permissible, it is very certain that, when it is not in our power to determine what is true, we ought to act according to what is most probable.

Descartes [1637], Part III

12.1 Reinforcement Learning Problem

12.2 Evolutionary Algorithms

12.3 Temporal Differences

12.4 Q-learning

12.5 Exploration and Exploitation

12.6 Evaluating Reinforcement Learning Algorithms

12.7 On-Policy Learning

12.8 Model-Based Reinforcement Learning

12.9 Reinforcement Learning with Features

12.10 Multiagent Reinforcement Learning

12.11 Review

12.12 References and Further Reading

12.13 Exercises