Self-supervised Reinforcement Learning with Independently Controllable Subgoals.
Andrii ZadaianchukGeorg MartiusFanny YangPublished in: CoRL (2021)
Keyphrases
- reinforcement learning
- state abstraction
- function approximation
- state space
- model free
- reinforcement learning algorithms
- temporal difference
- machine learning
- reinforcement learning methods
- learning process
- action selection
- optimal policy
- multi agent reinforcement learning
- transition model
- multi agent
- website
- artificial intelligence
- robot control
- robotic control
- function approximators
- databases
- control problems
- optimal control
- sufficient conditions
- supervised learning
- search space
- search algorithm
- neural network