foundations of computational agents
[W]e hypothesise that intelligence, and its associated abilities, can be understood as subserving the maximisation of reward. Accordingly, reward is enough to drive behaviour that exhibits abilities studied in natural and artificial intelligence, including knowledge, learning, perception, social intelligence, language, generalisation and imitation.
– Silver et al. 
A reinforcement learning (RL) agent acts in an environment, observing its state and receiving rewards. From its experience of a stream of acting then observing the resulting state and reward, it must determine what to do given its goal of maximizing accumulated reward. This chapter considers fully observable, single-agent reinforcement learning. Section describes multiagent reinforcement learning. This is an extension of decision-theoretic planning to the case where the transition and reward models are not specified.