NDLI: Dual Representations for Dynamic Programming and Reinforcement Learning

Content Provider	IEEE Xplore Digital Library
Author	Tao Wang Bowling, M. Schuurmans, D.
Copyright Year	2007
Description	Author affiliation: Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta. (Tao Wang; Bowling, M.; Schuurmans, D.)
Abstract	We investigate the dual approach to dynamic programming and reinforcement learning, based on maintaining an explicit representation of stationary distributions as opposed to value functions. A significant advantage of the dual approach is that it allows one to exploit well developed techniques for representing, approximating and estimating probability distributions, without running the risks associated with divergent value function estimation. A second advantage is that some distinct algorithms for the average reward and discounted reward case in the primal become unified under the dual. In this paper, we present a modified dual of the standard linear program that guarantees a globally normalized state visit distribution is obtained. With this reformulation, we then derive novel dual forms of dynamic programming, including policy evaluation, policy iteration and value iteration. Moreover, we derive dual formulations of temporal difference learning to obtain new forms of Sarsa and Q-learning. Finally, we scale these techniques up to large domains by introducing approximation, and develop new approximate off-policy learning algorithms that avoid the divergence problems associated with the primal approach. We show that the dual view yields a viable alternative to standard value function based techniques and opens new avenues for solving dynamic programming and reinforcement learning problems
Starting Page	44
Ending Page	51
File Size	186429
Page Count	8
File Format	PDF
ISBN	1424407060
DOI	10.1109/ADPRL.2007.368168
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2007-04-01
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Learning Heuristic algorithms Decision making Linear approximation Approximation algorithms Linear programming Probability distribution Dynamic programming Yield estimation Distributed computing
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

Dual representations for dynamic programming.

Diffusion gradient temporal difference for cooperative reinforcement learning with linear function approximation

Dynamic programming and reinforcement learning (adprl 2007) dual representations for dynamic programming and reinforcement learning.

Learning control of a bioreactor system using kernel-based heuristic dynamic programming

Value-gradient learning

Dual Representations for Dynamic Programming and Reinforcement Learning

Intelligent Model Learning Based on Variance for Bayesian Reinforcement Learning

Model-Free Dual Heuristic Dynamic Programming

Dual representations for dynamic programming and reinforcement learning.

Dual Representations for Dynamic Programming and Reinforcement Learning

Similar Documents

Dual representations for dynamic programming.

Diffusion gradient temporal difference for cooperative reinforcement learning with linear function approximation

Dynamic programming and reinforcement learning (adprl 2007) dual representations for dynamic programming and reinforcement learning.

Learning control of a bioreactor system using kernel-based heuristic dynamic programming

Value-gradient learning

Dual Representations for Dynamic Programming and Reinforcement Learning

Intelligent Model Learning Based on Variance for Bayesian Reinforcement Learning

Model-Free Dual Heuristic Dynamic Programming

Dual representations for dynamic programming and reinforcement learning.

Dual Representations for Dynamic Programming and Reinforcement Learning