• FINDER Search
• Submission
• Subscription
• About Us
• E-shop

JACIII Vol.13 No.6 Nov. 2009

Special Issue on New Trends in Reinforcement Learning

Editors : Kazuteru Miyazaki (National Institution for Academic Degrees and University Evaluation, Japan) and Keiki Takadama (The University of Electro-Comunications, Japan)

FINDER Search

• Table of Contents
• About this journal
• For Authors
• Back Numbers
• Contact

Editorial:

Special Issue on New Trends in Reinforcement Learning

Kazuteru Miyazaki and Keiki Takadama, pp. 599

Recently, the tailor-made system that grants an individual request has been recognized as the important approach. Such a system requires the “goal-directed learning” through interaction between user and system, which is mainly addressed in “reinforcement learning” domain.

This special issue on “New Trends in Reinforcement Learning” called for papers on the cuttingedge research exploring the goal-directed learning, which represents reinforcement learning. Many contributions were forthcoming, but we finally selected 12 works for publication. Although ”reinforcement learning” is included in the title of this special issue, the research works do not necessarily have to be on reinforcement learning itself, so long as the theme coincides with that of this special issue. In making our final selections, we gave special consideration to the kinds of research which can actively lead to new trends in reinforcement learning.

Of the 12 papers in this special issue, the first four mainly deal with the expansion of the reinforcement learning method in single agent environments. These cover a broad range of research, from works based on dynamic programming to exploitation-oriented methods.

The next two works deal with the Learning Classifier System (LCS), which applies the rule discovery mechanism to reinforcement learning. LCS is a technique with a long history, but for this issue, we were able to publish two theoretical works.

We are also grateful to Prof. Toshio Fukuda, Nagoya University, and Prof. Kaoru Hirota, Tokyo Institute of Technology, the editors-in-chief, and the NASTEC 2008 conference staff for inviting us to guest-edit this Journal.

The next four papers mainly deal with multi agent environments. We were able to draw from a wide range of research: from measuring interaction, through the expansion of techniques incorporating simultaneous learning, to research leading to application in multi agent environments.

The last two contributions mainly deal with application. We publish one paper on exemplar generalization and another detailing the successful application to government bond trading.

Each of these researches can be considered to be at the cutting-edge of reinforcement learning. We would like to end by saying that we hope this special issue constitutes a large contribution to the development of the field while holding a wide international appeal.

top

Paper:

Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning

Petar S. Kormushev, Kohei Nomoto, Fangyan Dong, and Kaoru Hirota, pp. 600-607

Abstract | Preview | Full Text (PDF417KB)

Paper:

Construction of Semi-Markov Decision Process Models of Continuous State Space Environments Using Growing Cell Structures and Multiagent k-Certainty Exploration Method

Takeshi Tateyama, Seiichi Kawata, and Yoshiki Shimomura, pp. 608-614

Abstract | Preview | Full-text (PDF585KB)

Paper:

About Profit Sharing Considering Infatuate Actions

Wataru Uemura, pp. 615-623

Abstract | Preview | Full-text (PDF224KB)

Paper:

Exploitation-Oriented Learning PS-r^#

Kazuteru Miyazaki and Shigenobu Kobayashi, pp. 624-630

Abstract | Preview | Full-text (PDF237KB)

Paper:

Analyzing Strength-Based Classifier System from Reinforcement Learning Perspective

Atsushi Wada and Keiki Takadama, pp. 631-639

Abstract | Preview | Full-text (PDF258KB)

top

Paper:

Is Gradient Descent Update Consistent with Accuracy-Based Learning Classifier System?

Atsushi Wada and Keiki Takadama, pp. 640-648

Abstract | Preview | Full-text (PDF247KB)

Paper:

Information Theoretic Approach for Measuring Interaction in Multiagent Domain

Sachiyo Arai and Yoshihisa Ishigaki, pp. 649-657

Abstract | Preview | Full-text (PDF491KB)

Paper:

Multiple-Timescale PIA for Model-Based Reinforcement Learning

Tomohiro Yamaguchi and Eri Imatani, pp. 658-666

Abstract | Preview | Full-text (PDF238KB)

Paper:

Time Horizon Generalization in Reinforcement Learning: Generalizing Multiple Q-Tables in Q-Learning Agents

Yasuyo Hatcho, Kiyohiko Hattori, and Keiki Takadama, pp. 667-674

Abstract | Preview | Full-text (PDF763KB)

Paper:

A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State Spaces

Takuji Watanabe, Kazuteru Miyazaki, and Hiroaki Kobayashi, pp. 675-682

Abstract | Preview | Full-text (PDF308KB)

top

Paper:

Exemplar Generalization in Reinforcement Learning: Improving Performance with Fewer Exemplars

Hiroyasu Matsushima, Kiyohiko Hattori, and Keiki Takadama, pp. 683-690

Abstract | Preview | Full-text (PDF610KB)

Paper:

Acquiring a Government Bond Trading Strategy Using Reinforcement Learning

Tohgoroh Matsui, Takashi Goto, and Kiyoshi Izumi, pp. 691-696

Abstract | Preview | Full-text (PDF511KB)

Regular Papers

Paper:

Capacity Expansion Problem by Monte Carlo Sampling Method

Takayuki Shiina, pp. 697-703

Abstract | Preview | Full-text (PDF139KB)

Paper:

Global Optimal Routing Algorithm for Traffic Systems with Multiple ODs

Yu Wang, Shingo Mabu, Shinji Eto, and Kotaro Hirasawa, pp. 704-712

Abstract | Preview | Full-text (PDF833KB)

Paper:

Traffic Flow Prediction with Genetic Network Programming (GNP)

Huiyu Zhou, Shingo Mabu, Wei Wei, Kaoru Shimada, and Kotaro Hirasawa, pp. 713-725

Abstract | Preview | Full-text (PDF515KB)

top

Paper:

Learning and Technical Market -Effects of In-Sample Data Selection-

Tomio Kurokawa, pp. 726-730

Abstract | Preview | Full-text (PDF146KB)

Paper:

Product-Impression Analysis Using Fuzzy C4.5 Decision Tree

Masataka Tokumaru and Noriaki Muranaka, pp. 731-737

Abstract | Preview | Full-text (PDF380KB)

top