ICRA 2012 Paper Abstract

Close

Paper TuA03.1

Hester, Todd (University of Texas at Austin), Quinlan, Michael (University of Texas at Austin), Stone, Peter (University of Texas at Austin)

RTMBA: A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control

Scheduled for presentation during the Regular Session "Learning and Adaptive Control of Robotic Systems I" (TuA03), Tuesday, May 15, 2012, 08:30−08:45, Meeting Room 3 (Mak'to)

2012 IEEE International Conference on Robotics and Automation, May 14-18, 2012, RiverCentre, Saint Paul, Minnesota, USA

This information is tentative and subject to change. Compiled on December 11, 2017

Keywords Learning and Adaptive Systems, Control Architectures and Programming, Autonomous Agents

Abstract

Reinforcement Learning (RL) is a paradigm for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few samples, while continually taking actions in real-time. Existing model-based RL methods learn in relatively few samples, but typically take too much time between each action for practical on-line learning. In this paper, we present a novel parallel architecture for model-based RL that runs in real-time by 1) taking advantage of sample-based approximate planning methods and 2) parallelizing the acting, model learning, and planning processes in a novel way such that the acting process is sufficiently fast for typical robot control cycles. We demonstrate that algorithms using this architecture perform nearly as well as methods using the typical sequential architecture when both are given unlimited time, and greatly out-perform these methods on tasks that require real-time actions such as controlling an autonomous vehicle.

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2017 PaperCept, Inc.
Page generated 2017-12-11  16:31:23 PST  Terms of use