Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Stochastic Grounded Action Transformation for Robot Learning in Simulation

Siddharth Desai, Haresh Karnan, Josiah P. Hanna, Garrett Warnell, and Peter Stone. Stochastic Grounded Action Transformation for Robot Learning in Simulation. In IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2020), October 2020.
11-minute video presentation.

Download

[PDF]1.9MB  

Abstract

Robot control policies learned in simulation do not often transfer well to the real world. Many existing solutions to this sim-to-real problem, such as the Grounded Action Transformation (GAT) algorithm, seek to correct for—or ground—these differences by matching the simulator tothe real world. However, the efficacy of these approaches is limited if they do not explicitly account for stochasticity inthe target environment. In this work, we analyze the prob-lems associated with grounding a deterministic simulator in astochastic real world environment, and we present examples where GAT fails to transfer a good policy due to stochastic transitions in the target domain. In response, we introduce the Stochastic Grounded Action Transformation (SGAT) algorithm, which models this stochasticity when grounding the simulator. We find experimentally—for both simulated and physical target domains—that SGAT can find policies that are robust to stochasticity in the target domain

BibTeX Entry

@InProceedings{IROS20-Desai,
author = {Siddharth Desai and Haresh Karnan and Josiah P. Hanna and Garrett Warnell and Peter Stone},
title = {Stochastic Grounded Action Transformation for Robot Learning in Simulation},
abstract = {Robot control policies learned in simulation do not often transfer well to the real world. Many existing solutions to this sim-to-real problem, such as the Grounded Action Transformation (GAT) algorithm, seek to correct for—or ground—these differences by matching the simulator tothe real world. However, the efficacy of these approaches is limited if they do not explicitly account for stochasticity inthe target environment. In this work, we analyze the prob-lems associated with grounding a deterministic simulator in astochastic real world environment, and we present examples where GAT fails to transfer a good policy due to stochastic transitions in the target domain. In response, we introduce the Stochastic Grounded Action Transformation (SGAT) algorithm, which models this stochasticity when grounding the simulator. We find experimentally—for both simulated and physical target domains—that SGAT can find policies that are robust to stochasticity in the target domain},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2020)},
month = {October},
year = {2020},
location = {Las Vegas, NV, USA},
wwwnote={<a href="https://youtu.be/rz1s7uft-ow">11-minute video presentation</a>.},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 21:30:59