A Mixture of Surprises for Unsupervised Reinforcement Learning.
Andrew ZhaoMatthieu Gaetan LinYangguang LiYong-Jin LiuGao HuangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- unsupervised learning
- supervised learning
- mixture model
- function approximation
- finite mixture model
- expectation maximization
- semi supervised
- multi agent reinforcement learning
- reinforcement learning algorithms
- learning algorithm
- temporal difference
- markov decision processes
- autonomous learning
- data sets
- action selection
- robotic control
- optimal policy
- data driven
- dynamic programming
- multi agent
- supervised classification
- model free
- markov decision process
- state space
- density estimation
- topic modeling
- gaussian mixture model
- dirichlet distribution
- neural network