Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration.
Jinning LiXinyi LiuBanghua ZhuJiantao JiaoMasayoshi TomizukaChen TangWei ZhanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- online learning
- learning algorithm
- balancing exploration and exploitation
- robot programming
- model free
- function approximation
- learning problems
- dynamic programming
- machine learning
- supervised learning
- state space
- optimal policy
- markov decision processes
- expert systems
- case study
- temporal difference
- online services
- data sets