1

PILCO: A Model-Based and Data-Efficient Approach to Policy Search
PDF Cite Code
State-Space Inference and Learning with Gaussian Processes
PDF Cite
Analytic Moment-based Gaussian Process Filtering
We propose an analytic moment-based filter for nonlinear stochastic dynamic systems modeled by Gaussian processes. Exact expressions …
PDF Cite
Efficient Reinforcement Learning for Motor Control
PDF Cite
Approximate Dynamic Programming with Gaussian Processes
In general, it is difficult to determine an optimal closed-loop policy in nonlinear control problems with continuous-valued state and …
PDF Cite
Model-Based Reinforcement Learning with Continuous States and Actions
Finding an optimal policy in a reinforcement learning (RL) framework with continuous state and action spaces is challenging. …
PDF Cite
Probabilistic Inference for Fast Learning in Control
PDF Cite
Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces
A novel online-computation approach to optimal control of nonlinear, noise-affected systems with continuous state and control spaces is …
PDF Cite
Finite-Horizon Optimal State Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle
In this paper, an approach to the finite-horizon optimal state-feedback control problem of nonlinear, stochastic. discrete-time systems …
PDF Cite DOI