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