Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap.
Mohammad MehrabiStefan WagerPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- policy evaluation
- policy iteration
- reinforcement learning
- state space
- finite state
- optimal policy
- dynamic programming
- planning under uncertainty
- action space
- infinite horizon
- average reward
- reinforcement learning algorithms
- partially observable
- decision processes
- average cost
- markov decision process
- least squares
- model free
- markov decision problems
- partially observable markov decision processes
- reward function
- machine learning