Explaining Reinforcement Learning with Shapley Values.
Daniel BeecheyThomas M. S. SmithÖzgür SimsekPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- parameter values
- reinforcement learning algorithms
- function approximation
- markov decision processes
- learning algorithm
- attribute values
- dynamic programming
- user defined
- multi agent
- e learning
- search engine
- model free
- action selection
- temporal difference
- data mining
- robotic control
- generating explanations