Work

Learning of non-parametric control policies with high-dimensional state features

Year: 2015

Type: article

Abstract: Learning complex control policies from highdimensional sensory input is a challenge forreinforcement learning algorithms. Kernel methods that approximate values functionsor transition models can address this problem. Yet, many current approaches rely oninstable greedy maximization. In this paper, we develop a policy search algorithm thatintegrates robust policy updates and kernel embeddings. Our method can learn nonparametriccontrol policies for infinite horizon continuous MDPs with high-dimensionalsensory representations. We show that our method outperforms related approaches, andthat our algorithm can learn an underpowered swing-up task task directly from highdimensionalimage data.

Source: Lincoln Repository (University of Lincoln)

Authors: Herke van Hoof, Jan Peters, Gerhard Neumann

Institutions: Technische Universität Darmstadt, Max Planck Society, Max Planck Institute for Intelligent Systems

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Awards: Composing Learning for Artificial Cognitive Systems, Tactile Manipulation

OpenAlex ID: W314779054