Improving Generalization in Reinforcement Learning with Mixture Regularization.
Kaixin WangBingyi KangJie ShaoJiashi FengPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- mixture model
- state space
- function approximation
- model free
- expectation maximization
- markov decision processes
- optimal policy
- robotic control
- data dependent
- gaussian mixture model
- data sets
- machine learning
- transfer learning
- markov random field
- supervised learning
- probability distribution
- regularization framework