Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes.
Mengdi XuWenhao DingJiacheng ZhuZuxin LiuBaiming ChenDing ZhaoPublished in: NeurIPS (2020)
Keyphrases
- gaussian processes
- reinforcement learning
- dirichlet process
- gaussian process
- gaussian process regression
- multitask learning
- covariance function
- relational reinforcement learning
- preference learning
- multi task learning
- gaussian process models
- human pose estimation
- relevance vector machine
- multi task
- mixture model
- machine learning
- noise reduction
- closed form
- cross validation
- model selection
- state space
- decision trees