ASPiRe: Adaptive Skill Priors for Reinforcement Learning.
Mengda XuManuela VelosoShuran SongPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- database systems
- dynamic programming
- adaptive control
- model free
- learning algorithm
- supervised learning
- prior probabilities
- reinforcement learning algorithms
- temporal difference
- optimal control
- database applications
- state space
- mobile robot
- learning environment
- multi agent
- image segmentation