Predictive Explanations for and by Reinforcement Learning.
Léo SaulièresMartin C. CooperFlorence Dupin de Saint-CyrPublished in: ICAART (Revised Selected Paper) (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- state space
- machine learning
- robotic control
- optimal policy
- action selection
- temporal difference
- generating explanations
- markov decision processes
- hidden markov models
- learning algorithm
- control problems
- predictive modeling
- action space
- neural network