Bootstrapped Transformer for Offline Reinforcement Learning.
Kerong WangHanye ZhaoXufang LuoKan RenWeinan ZhangDongsheng LiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- dynamic programming
- function approximation
- fuzzy logic
- state space
- machine learning
- optimal policy
- real time
- temporal difference learning
- markov decision processes
- temporal difference
- multi agent reinforcement learning
- fault diagnosis
- model free
- relational reinforcement learning
- robotic control
- reinforcement learning algorithms
- direct policy search
- action selection
- optimal control
- learning problems
- power system
- genetic algorithm
- action space
- learning process
- transition model
- learning environment
- multi agent