A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning.
Martha WhiteAdam M. WhitePublished in: CoRR (2016)
Keyphrases
- temporal difference learning
- fixed point
- function approximation
- reinforcement learning
- approximate value iteration
- evaluation function
- game playing
- temporal difference
- reinforcement learning algorithms
- feature selection
- monte carlo
- dynamic programming
- neural network
- markov decision process
- search algorithm
- particle swarm optimization
- probabilistic model
- function approximators