foundations of computational agents
For an introduction to reinforcement learning, see Szepesvári , Sutton and Barto , and Kaelbling et al. . Bertsekas and Tsitsiklis  investigate function approximation and its interaction with reinforcement learning. Powell  describes various applications of reinforcement learning to energy systems.
Mnih et al.  describe how reinforcement learning combined with neural networks was used to solve classic Atari computer games, and Silver et al.  show how learning can be used for the game of Go.