Temporal Difference Learning and TD-Gammon.
Gerald TesauroPublished in: J. Int. Comput. Games Assoc. (1995)
Keyphrases
- temporal difference learning
- function approximation
- temporal difference
- fixed point
- reinforcement learning
- game playing
- evaluation function
- approximate value iteration
- reinforcement learning algorithms
- markov decision process
- markov decision processes
- linear combination
- dynamic environments
- model free
- policy iteration
- function approximators
- least squares