Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning.
Jongwook ChoiArchit SharmaHonglak LeeSergey LevineShixiang Shane GuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning capabilities
- learning problems
- learning systems
- learning community
- online learning
- supervised learning
- machine learning
- learning tasks
- prior knowledge
- function approximation
- variational methods
- temporal difference learning
- previously learned
- mobile robot
- optical flow
- evaluation function
- multi agent
- model free
- image segmentation
- learned knowledge