Offline Meta-Reinforcement Learning with Online Self-Supervision.
Vitchyr H. PongAshvin NairLaura SmithCatherine HuangSergey LevinePublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- online learning
- active learning
- state space
- real time
- machine learning
- artificial intelligence
- learning algorithm
- robotic control
- multi agent
- learning process
- markov decision processes
- function approximation
- balancing exploration and exploitation
- temporal difference
- meta level
- least squares
- search algorithm
- data mining
- real world