Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions.
Omer GottesmanJoseph FutomaYao LiuSonali ParbhooLeo A. CeliEmma BrunskillFinale Doshi-VelezPublished in: ICML (2020)
Keyphrases
- policy evaluation
- reinforcement learning
- temporal difference
- least squares
- model free
- monte carlo
- function approximation
- markov decision processes
- policy iteration
- td learning
- variance reduction
- reinforcement learning algorithms
- optimal policy
- state space
- learning algorithm
- semi parametric
- multi agent
- image sequences
- markov chain
- reinforcement learning methods
- statistical inference
- evaluation function
- supervised learning
- transfer learning
- markov decision problems
- machine learning
- neural network