Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyond.
Chun Kai LingKian Hsiang LowPatrick JailletPublished in: CoRR (2015)
Keyphrases
- gaussian process
- gaussian processes
- active learning
- semi supervised
- reward function
- hyperparameters
- marginal likelihood
- gaussian process regression
- approximate inference
- expectation propagation
- model selection
- regression model
- fully bayesian
- bayesian framework
- random sampling
- posterior distribution
- gaussian process models
- reinforcement learning
- latent variables
- bayesian methods
- multiple agents
- inverse reinforcement learning
- state variables
- bayesian networks
- markov decision processes
- cross validation
- maximum likelihood
- state space
- probability distribution
- maximum entropy
- posterior probability
- decision theory
- prior information
- pairwise
- machine learning