NDLI: An error-sensitive Q-learning approach for robot navigation

Content Provider	IEEE Xplore Digital Library
Author	Rongkuan Tang Hongliang Yuan
Copyright Year	2015
Description	Author affiliation: Coll. of Electron. & Inf., Tongji Univ., Shanghai, China (Rongkuan Tang; Hongliang Yuan)
Abstract	Reinforcement learning can capture notions of optimal behavior occurring in natural systems. In the context of reinforcement learning, the learning rate controls how fast we modify our estimates. Generally Q-learning approach leverages the temporal-difference (TD) error to regulate Q-value, while utilizing a constant or decreasing learning rate, e.g., linear or polynomial learning rate, throughout the agent's life. Learning algorithm with polynomial learning rate learns faster at the cost of inferior trade-off between exploration and exploitation. None of them is evaluated based on the TD error. Whereas that cannot psychologically reflect the agent's true learning progress with unnecessary extra training episodes and exploration. This paper proposes an error-sensitive learning rate mechanism for Q-learning algorithm termed as (ESQL) to achieve better mitigation and faster learning. The agent is endowed sensibility to the TD error summed over the episodes. The derived method is implemented with indoor robot navigation task simulation in a stationary grid world environment. Experimental results are presented showing that ESQL approach achieves faster learning and latent better trade-off between exploration and exploitation compared with both constant and decreasing learning rate Q-learning approaches.
Starting Page	5835
Ending Page	5840
File Size	344811
Page Count	6
File Format	PDF
ISBN	9789881563897
ISSN	19341768
DOI	10.1109/ChiCC.2015.7260552
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-07-28
Publisher Place	China
Access Restriction	Subscribed
Rights Holder	Technical Committee on Control Theory, Chinese Association of Automation
Subject Keyword	Machine learning algorithms Q-learning Navigation Heuristic algorithms Robot navigation Learning rate Reinforcement learning Training TD error Error-sensitive Learning (artificial intelligence) Polynomials Robots
Content Type	Text
Resource Type	Article

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

The Strategy Entropy of Reinforcement Learning for Mobile Robot Navigation in Complex Environments

Omnidirectional mobile robots navigation: A joint approach combining reinforcement learning and knowledge-based systems

Enhanced learning classifier system for robot navigation

An improved Q-learning algorithm for an autonomous mobile robot navigation problem

Q learning for mobile robot navigation in indoor environment

A reinforcement-learning approach to robot navigation

Implementation of Reinforcement Learning by transfering sub-goal policies in robot navigation

Reinforcement learning algorithms for robotic navigation in dynamic environments

On reinforcement learning for robots

An error-sensitive Q-learning approach for robot navigation

Similar Documents

The Strategy Entropy of Reinforcement Learning for Mobile Robot Navigation in Complex Environments

Omnidirectional mobile robots navigation: A joint approach combining reinforcement learning and knowledge-based systems

Enhanced learning classifier system for robot navigation

An improved Q-learning algorithm for an autonomous mobile robot navigation problem

Q learning for mobile robot navigation in indoor environment

A reinforcement-learning approach to robot navigation

Implementation of Reinforcement Learning by transfering sub-goal policies in robot navigation

Reinforcement learning algorithms for robotic navigation in dynamic environments

On reinforcement learning for robots

An error-sensitive Q-learning approach for robot navigation