Unsupervised Reinforcement Learning with Contrastive Intrinsic Control.
Michael LaskinHao LiuXue Bin PengDenis YaratsAravind RajeswaranPieter AbbeelPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- supervised learning
- robot control
- function approximation
- control system
- control policy
- learning algorithm
- process control
- control strategy
- unsupervised learning
- state space
- dynamic programming
- robotic control
- optimal policy
- data driven
- semi supervised
- control method
- learning process
- machine learning