… Gaussian Process Temporal Difference (GPTD) learning offers a Bayesian solution to the
policy evaluation problem of reinforcemcnt learning. In … of the value Gaussian process. We also …

… In the current paper we use Gaussian process (GP) models for two distinct purposes: first to
model the dynamics of the system (actually, we use one GP per dimension of the state space…

… be predicted using Gaussian process regression models, … reinforcement learning is the
value function, which describes the long-term strategic value of a state. Using Gaussian process …

… In this paper, we extend the Gaussian process model to learn … Our Gaussian Process
Inverse Reinforcement Learning (… describe how Gaussian processes can be used to learn r as …

… used in reinforcement learning to learn a controller … Gaussian Processes for learning
predictive models is described in Section IV. A blimp controller is built using reinforcement learning …

… To solve this time-series POMDP, we propose a novel Gaussian process reinforcement
learning (GPRL) based solution. It achieves accurate channel selection and a fast learning rate. …

… This article proposes an efficient way to solve the IRL problem based on the sparse Gaussian
process (GP) prediction with l1-regularization only using a highly limited number of expert …

… To deal with problems in large or even infinite state space, we propose a Gaussian process
model and use preference graphs to represent observations of decision trajectories. Our …

… learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of
learning … Our model stacks multiple latent GP layers to learn abstract representations of the …

… In this paper, we frame meta learning as a hierarchical latent variable model and infer the …
modelbased reinforcement learning setting and show that our meta-learning model effectively …