Learning a subspace of policies for online adaptation in Reinforcement Learning.
Jean-Baptiste GayaLaure SoulierLudovic DenoyerPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- online learning
- learning algorithm
- learning process
- learning tasks
- learning problems
- supervised learning
- continuous state
- state space
- high dimensional
- learning systems
- hierarchical reinforcement learning
- autonomous learning
- adaptive learning
- action selection
- balancing exploration and exploitation
- state abstraction
- learning agents
- robot control
- learning capabilities
- e learning
- neural network
- mobile learning
- active learning