A Mixture Of Surprises for Unsupervised Reinforcement Learning.
Andrew ZhaoMatthieu Gaetan LinYangguang LiYong-Jin LiuGao HuangPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- unsupervised learning
- supervised learning
- mixture model
- finite mixture model
- model free
- learning algorithm
- function approximation
- state space
- completely unsupervised
- expectation maximization
- multi agent
- semi supervised
- data driven
- learning process
- optimal control
- reinforcement learning algorithms
- data sets
- maximum likelihood
- transfer learning
- supervised classification
- bayesian networks
- robot control
- unsupervised manner
- temporal difference learning
- transition model
- machine learning