Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning.
Dingwen KongLin F. YangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- partially observable environments
- function approximation
- learning agent
- learning problems
- online learning
- reinforcement learning methods
- dynamic programming
- optimal policy
- markov decision processes
- learning tasks
- actor critic
- multi agent
- prior knowledge
- inverse reinforcement learning
- autonomous learning
- partially observable
- learning capabilities
- model free
- solving problems
- supervised learning