EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model.
Yifu YuanJianye HaoFei NiYao MuYan ZhengYujing HuJinyi LiuYingfeng ChenChangjie FanPublished in: ICLR (2023)
Keyphrases
- reinforcement learning
- computational model
- probability distribution
- probabilistic model
- mathematical model
- management system
- machine learning
- formal model
- prior knowledge
- image segmentation
- decision making
- pairwise
- em algorithm
- theoretical analysis
- feature selection
- theoretical framework
- learning algorithm
- experimental data
- neural network model
- data sets
- prediction model
- transition model