Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning.
Tongzhou WangAntonio TorralbaPhillip IsolaAmy ZhangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning process
- supervised learning
- learning algorithm
- unsupervised learning
- learning systems
- learning tasks
- learning problems
- optimal control
- action selection
- online learning
- eligibility traces
- learned knowledge
- active exploration
- actor critic
- evolutionary learning
- autonomous learning
- learning capabilities
- function approximation
- knowledge acquisition