State-Action Similarity-Based Representations for Off-Policy Evaluation.
Brahma S. PavseJosiah HannaPublished in: NeurIPS (2023)
Keyphrases
- state action
- reinforcement learning
- temporal difference
- function approximators
- policy iteration
- evaluation function
- average reward
- markov decision process
- function approximation
- policy gradient
- model free
- least squares
- stochastic games
- markov decision processes
- action space
- monte carlo
- optimal policy
- reinforcement learning algorithms
- action selection
- dynamic programming
- machine learning