Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning.
Sasha SalterKristian HartikainenWalter GoodwinIngmar PosnerPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- information asymmetry
- transfer learning
- function approximation
- model free
- reinforcement learning algorithms
- state space
- behavioural cloning
- hierarchical structure
- multi agent
- knowledge transfer
- markov decision processes
- prior information
- dynamic programming
- temporal difference
- learning algorithm
- optimal policy
- bayesian framework
- supervised learning
- action selection
- prior knowledge
- reinforcement learning methods
- previously learned
- learning tasks
- transferring knowledge