Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning.
Tongzhou WangAntonio TorralbaPhillip IsolaAmy ZhangPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- dynamic programming
- learning systems
- prior knowledge
- online learning
- function approximation
- state space
- eligibility traces
- reinforcement learning methods
- learning agents
- learning tasks
- markov decision processes
- supervised learning
- support vector
- optimal solution