Autonomous Reinforcement Learning: Formalism and Benchmarking.
Archit SharmaKelvin XuNikhil SardanaAbhishek GuptaKarol HausmanSergey LevineChelsea FinnPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- autonomous learning
- function approximation
- state space
- learning capabilities
- cooperative
- model free
- markov decision processes
- multi agent
- autonomous mental development
- knowledge representation
- formal model
- semi autonomous
- autonomous navigation
- temporal difference
- robotic control
- computational properties
- tree adjoining grammar
- optimal control
- robotic systems
- optimal policy
- reinforcement learning algorithms
- action selection
- autonomous systems
- learning agents
- temporal difference learning
- formal theory
- transfer learning
- description logics