Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning.
Huy HoangTien MaiPradeep VarakanthamPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- function approximation
- incremental learning
- robotic control
- markov decision processes
- state space
- optimal policy
- control problems
- reinforcement learning algorithms
- model free
- machine learning
- search algorithm
- neural network
- incremental version
- multi agent reinforcement learning
- learning algorithm
- transfer learning
- temporal difference
- information systems
- single pass
- batch mode
- temporal difference learning
- reinforcement learning methods
- sufficient conditions
- incremental clustering
- supervised learning
- dynamic programming