Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery.
Yiqin YangHao HuWenzhe LiSiyuan LiJun YangQianchuan ZhaoChongjie ZhangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal control
- control problems
- data mining
- robot control
- function approximation
- knowledge discovery
- markov decision processes
- control strategies
- state space
- dynamic programming
- web services
- image compression
- optimal policy
- real time
- learning tasks
- control strategy
- mobile robot
- control method
- high level
- lossless compression
- learning algorithm
- control policy
- robotic control