Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions.
Omer GottesmanJoseph FutomaYao LiuSonali ParbhooLeo Anthony CeliEmma BrunskillFinale Doshi-VelezPublished in: CoRR (2020)
Keyphrases
- policy evaluation
- reinforcement learning
- temporal difference
- least squares
- model free
- monte carlo
- policy iteration
- function approximation
- markov decision processes
- td learning
- variance reduction
- reinforcement learning algorithms
- semi parametric
- optimal policy
- machine learning
- multi agent
- state space
- action selection
- partially observable markov decision processes
- decision making
- state transitions
- learning algorithm
- supervised learning
- optimal control
- decision trees
- dynamic programming
- statistical inference
- belief revision
- markov decision problems