Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning.
Mohammadreza NakhaeiAidan ScannellJoni PajarinenPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- online learning
- learning algorithm
- learning problems
- learning capabilities
- supervised learning
- learning process
- real time
- adaptive control
- learning systems
- learning agents
- temporal difference learning
- reinforcement learning methods
- context aware
- contextual information
- function approximation
- learning community
- learning agent
- evolutionary learning