Reducing Sampling Error in Batch Temporal Difference Learning.
Brahma S. PavseIshan DurugkarJosiah HannaPeter StonePublished in: CoRR (2020)
Keyphrases
- temporal difference learning
- fixed point
- function approximation
- evaluation function
- monte carlo
- game playing
- reinforcement learning
- temporal difference
- approximate value iteration
- markov decision process
- random sampling
- neural network
- search space
- dynamic programming
- graph cuts
- learning tasks
- decision making
- machine learning