Counterfactual Explanation Policies in RL.
Shripad Vilasrao DeshmukhSrivatsan RSupriti VijayJayakumar SubramanianChirag AgarwalPublished in: CoRR (2023)
Keyphrases
- optimal policy
- reinforcement learning
- causal reasoning
- control policies
- control policy
- markov decision process
- state space
- markov decision processes
- dynamic programming
- reinforcement learning algorithms
- multiagent reinforcement learning
- policy search
- function approximation
- reward function
- model free
- revenue management
- markov decision problems
- logical framework
- decision problems
- multi agent
- action space
- policy iteration
- learning algorithm
- autonomous learning
- finite state
- total reward
- generating explanations
- semi markov decision process