CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations.
Kai YanAlexander G. SchwingYu-Xiong WangPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- explicit feedback
- state space
- function approximation
- explicit knowledge
- dynamic programming
- reinforcement learning algorithms
- robotic control
- bayesian framework
- optimal control
- learned from training data
- real robot
- learning capabilities
- model free
- combining multiple
- real world
- probability distribution
- artificial neural networks
- multi agent
- learning algorithm