Explainable Deep Reinforcement Learning: State of the Art and Challenges.
George A. VourosPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- lessons learned
- function approximation
- multi agent
- real world
- learning algorithm
- reinforcement learning algorithms
- key issues
- state space
- application scenarios
- markov decision processes
- robotic control
- temporal difference learning
- action space
- technical challenges
- temporal difference
- model free
- optimal policy
- supervised learning
- control system
- learning environment
- information systems
- genetic algorithm