A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning.
Martha WhiteAdam M. WhitePublished in: AAMAS (2016)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- game playing
- evaluation function
- temporal difference
- reinforcement learning
- approximate value iteration
- search algorithm
- feature selection
- markov decision process
- dynamic programming
- sufficient conditions
- reinforcement learning algorithms
- least squares
- linear combination