Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement Learning.
Noah Y. SiegelJost Tobias SpringenbergFelix BerkenkampAbbas AbdolmalekiMichael NeunertThomas LampeRoland HafnerNicolas HeessMartin A. RiedmillerPublished in: ICLR (2020)
Keyphrases
- reinforcement learning
- real time
- learning algorithm
- function approximation
- multi agent
- state space
- real robot
- model free
- learning process
- optimal policy
- mobile robot
- robotic control
- autonomous learning
- behavior analysis
- human behavior
- markov decision processes
- image segmentation
- genetic algorithm
- machine learning
- real world
- data sets