Offline Meta-Reinforcement Learning with Online Self-Supervision.
Vitchyr H. PongAshvin V. NairLaura M. SmithCatherine HuangSergey LevinePublished in: ICML (2022)
Keyphrases
- reinforcement learning
- real time
- online learning
- function approximation
- reinforcement learning algorithms
- machine learning
- learning algorithm
- state space
- online algorithms
- data sets
- artificial neural networks
- hidden markov models
- multi agent
- objective function
- evaluation function
- search engine
- partially observable
- cross cultural
- database