Reinforcement Learning Explained via Reinforcement Learning: Towards Explainable Policies through Predictive Explanation.
Léo SaulièresMartin C. CooperFlorence BannayPublished in: ICAART (2) (2023)
Keyphrases
- reinforcement learning
- optimal policy
- function approximation
- policy search
- markov decision processes
- model free
- learning algorithm
- markov decision process
- reinforcement learning algorithms
- fitted q iteration
- robotic control
- hierarchical reinforcement learning
- markov decision problems
- state space
- machine learning
- control policies
- stochastic approximation
- learning process
- temporal difference learning
- data sets
- multi agent
- temporal difference
- sufficient conditions
- learning capabilities
- hidden markov models
- search space
- reward function
- state and action spaces
- neural network
- supervised learning