RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning.
Jasmina GajcinIvana DusparicPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- temporal difference
- optimal policy
- reinforcement learning algorithms
- model free
- generating explanations
- temporal difference learning
- action selection
- markov decision processes
- learning process
- learning algorithm
- machine learning
- real time
- dynamic programming
- domain knowledge
- hidden markov models
- multi agent
- logical framework
- data sets
- policy search