Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes.
Andrew BennettNathan KallusPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- policy evaluation
- reinforcement learning
- policy iteration
- partially observed
- optimal policy
- temporal difference
- least squares
- reinforcement learning algorithms
- model free
- state space
- finite state
- monte carlo
- function approximation
- state and action spaces
- dynamic programming
- partially observable
- average reward
- action space
- planning under uncertainty
- markov decision process
- variance reduction
- infinite horizon
- machine learning
- markov decision problems
- decision processes
- partially observable markov decision processes
- average cost
- linear programming
- reward function
- decision problems
- optical flow
- learning algorithm
- optimal control