Self-supervised Reinforcement Learning with Independently Controllable Subgoals.
Andrii ZadaianchukGeorg MartiusFanny YangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- state abstraction
- function approximation
- temporal difference
- optimal policy
- reinforcement learning algorithms
- state space
- learning algorithm
- supervised learning
- learning process
- decision trees
- multi agent
- function approximators
- robotic control
- sufficient conditions
- model free
- partially observable
- control problems
- reinforcement learning methods
- machine learning