NDLI: The importance of variance reduction in policy gradient method

Content Provider	IEEE Xplore Digital Library
Author	Tak Kit Lau Yun-hui Liu
Copyright Year	2012
Description	Author affiliation: Dept. of Mech. & Autom. Eng., Chinese Univ. of Hong Kong, Hong Kong, China (Tak Kit Lau; Yun-hui Liu)
Abstract	Reinforcement learning (RL) has been applied to a wide range of motion control problems in robotics. In particular, policy gradient method (PGM) emerges as a powerful subset of RL that can learn effectively from one's experience. However, when the dynamics is stochastic and is short of samples for learning, the performance of PGM becomes inconsistent and heavily relies on the tweaking of the learning rate. In this work, we argue that this degeneration is mainly due to the high variance in the gradient. Through theoretical justifications, simulations and experiments, we verify that by applying a variance suppression, which is called local baseline, on the gradient, PGM can then be applied to some previously untouchable problems.
Sponsorship	IEEE Control Syst. Soc.
Starting Page	1376
Ending Page	1381
File Size	1281004
Page Count	6
File Format	PDF
ISBN	9781457710957
ISSN	07431619
e-ISBN	9781457710964
e-ISBN	9781467321020
DOI	10.1109/ACC.2012.6315368
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2012-06-27
Publisher Place	Canada
Access Restriction	Subscribed
Rights Holder	American Automatic Control Council(AACC)
Subject Keyword	Uncertainty Gradient methods Robots Cost function Trajectory Heuristic algorithms Algorithm design and analysis
Content Type	Text
Resource Type	Article
Subject	Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Stunt driving via policy search

Learning of closed-loop motion control

Multi-cost robotic motion planning under uncertainty

A source-based algorithm for delay-constrained minimum-cost multicasting

Uncertainty Reduction via Heuristic Search Planning on Hybrid Metric/Topological Map

PRISCA: A policy search method for extreme trajectory following

Importance sampling actor-critic algorithms.

A method for path planning of autonomous robot using A∗ algorithm

Discrete Partitioning and Coverage Control for Gossiping Robots

The importance of variance reduction in policy gradient method

Similar Documents

Stunt driving via policy search

Learning of closed-loop motion control

Multi-cost robotic motion planning under uncertainty

A source-based algorithm for delay-constrained minimum-cost multicasting

Uncertainty Reduction via Heuristic Search Planning on Hybrid Metric/Topological Map

PRISCA: A policy search method for extreme trajectory following

Importance sampling actor-critic algorithms.

A method for path planning of autonomous robot using A∗ algorithm

Discrete Partitioning and Coverage Control for Gossiping Robots

The importance of variance reduction in policy gradient method