Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning.
Nathan KallusAngela ZhouPublished in: CoRR (2020)
Keyphrases
- infinite horizon
- policy evaluation
- policy iteration
- markov decision processes
- reinforcement learning
- optimal policy
- optimal control
- finite horizon
- temporal difference
- state space
- model free
- markov decision process
- dynamic programming
- partially observable markov decision processes
- least squares
- partially observable
- reinforcement learning algorithms
- long run
- function approximation
- markov decision problems
- average cost
- finite state
- average reward
- decision problems
- multistage
- machine learning
- fixed point
- monte carlo
- lost sales
- lead time
- decision processes
- linear programming
- learning algorithm