Learning Object-conditioned Exploration using Distributed Soft Actor Critic.
Ayzaan WahidAustin StoneKevin ChenBrian IchterAlexander ToshevPublished in: CoRL (2020)
Keyphrases
- learning objects
- actor critic
- learning resources
- adaptive learning
- learning management systems
- e learning
- learning process
- learning activities
- learning object metadata
- metadata
- policy gradient
- learning object repositories
- multi agent
- gradient method
- least squares
- active learning
- neuro fuzzy
- function approximation
- temporal difference
- average reward
- reinforcement learning