Skill-based Meta-Reinforcement Learning.
Taewook NamShao-Hua SunKarl PertschSung Ju HwangJoseph J. LimPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- meta level
- state space
- reinforcement learning algorithms
- transfer learning
- model free
- markov decision processes
- search results clustering
- robotic control
- learning process
- decision making
- control problems
- optimal control
- temporal difference learning
- learning agents
- direct policy search
- partially observable
- action selection
- real time
- learning problems
- optimal policy
- multi agent
- learning algorithm