Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning.
Huy HoangTien MaiPradeep VarakanthamPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- incremental learning
- markov decision processes
- function approximation
- reinforcement learning algorithms
- multi agent
- temporal difference
- model free
- optimal policy
- learning algorithm
- incremental clustering
- data driven
- multi agent reinforcement learning
- incremental version
- evaluation function
- learning problems
- supervised learning
- artificial intelligence
- partially observable
- markov decision process
- batch mode
- reinforcement learning methods
- incremental algorithms
- data sets
- policy search
- direct policy search