Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes.
Mengdi XuWenhao DingJiacheng ZhuZuxin LiuBaiming ChenDing ZhaoPublished in: CoRR (2020)
Keyphrases
- gaussian processes
- reinforcement learning
- gaussian process
- dirichlet process
- gaussian process regression
- relational reinforcement learning
- covariance function
- multitask learning
- multi task learning
- preference learning
- gaussian process models
- multi task
- human pose estimation
- learning algorithm
- relevance vector machine
- hyperparameters
- image reconstruction
- mixture model
- text mining
- text classification
- state space
- prior knowledge
- error rate
- labeled data
- model selection