Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning.
Cameron VoloshinHoang Minh LeNan JiangYisong YuePublished in: CoRR (2019)
Keyphrases
- empirical studies
- policy evaluation
- reinforcement learning
- temporal difference
- least squares
- model free
- function approximation
- policy iteration
- monte carlo
- markov decision processes
- variance reduction
- empirical analysis
- td learning
- reinforcement learning algorithms
- optimal policy
- state space
- multi agent
- semi parametric
- reinforcement learning methods
- step size
- partially observable markov decision processes
- function approximators
- learning algorithm
- machine learning
- partially observable
- dynamic programming