Machine learning has been attracting significant attention again since the potential of deep learning was recognized. Not only has machine learning been improved, but it has also been integrated with “reinforcement learning,” revealing other potential applications, e.g., deep Q-networks (DQN) and AlphaGO proposed by Google DeepMind. It is against this background that this special issue, “Cutting Edge of Reinforcement Learning and its Hybrid Methods,” focuses on both reinforcement learning and its hybrid methods, including reinforcement learning with deep learning or evolutionary computation, to explore new potentials of reinforcement learning.

Of the many contributions received, we finally selected 13 works for publication. The first three propose hybrids of deep learning and reinforcement learning for single agent environments, which include the latest research results in the areas of convolutional neural networks and DQN. The fourth through seventh works are related to the Learning Classifier System, which integrates evolutionary computation and reinforcement learning to develop the rule discovery mechanism. The eighth and ninth works address problems related to goal design or the reward, an issue that is particularly important to the application of reinforcement learning. The last four contributions deal with multiagent environments.

These works cover a wide range of studies, from the expansion of techniques incorporating simultaneous learning to applications in multiagent environments. All works are on the cutting edge of reinforcement learning and its hybrid methods. We hope that this special issue constitutes a large contribution to the development of the reinforcement learning field.

Six years have passed since the publication of our Special Issue on Human-Robot Interaction Systems in 2011. Since then, artificial intelligence and robotics have developed rapidly, and the opportunities for human beings and robots to work together have increased. The objective of this special issue’s twelve articles is to activate and expand high-quality research.

In the first article, Y. Tamura, T. Akashi, and H. Osumi propose a computational model of robot’s gaze. In the second article, S. Hoshino and K. Uchida propose an interactive motion planner for robot navigation in dynamic environments. In the third article, T. Iio, Y. Yoshikawa, and H. Ishiguro develop a conversational robotic system based on human response. In the fourth article, K. Sakai, F. Dalla Libera, Y. Yoshikawa, and H. Ishiguro propose a method for generating bystander robots’ actions that is based on an analysis of the relative probabilities of human responses to robot actions. In the fifth article, T. Matsumaru and M. Narita present a newly developed support system for learning calligraphy strokes. In the sixth article, E. Tamura, Y. Yamashita, T. Yamashita, E. Sato-Shimokawara, and T. Yamaguchi present a method of driving a car simply by gesturing. In the seventh article, A. Kurosu and T. Hashimoto develop an eye robot with two degrees of freedom. It is intended for use as a communication robot. In the eighth article, T. Hashimoto, Y. Munakata, R. Yamanaka, and A. Kurosu report on a method for retrieving episodic memories. In the ninth article, Y. Nishikawa, Y. Kagawa, and A. Okazaki develop a spiral movement robot for inpatients. In the tenth article, Y. Umesawa, K. Doi, and H. Fujimoto develop an interface device that creates kinaesthetic illusions by inducing vibrations in muscle tendons, vibrations that coordinate with dual-joint movements. In the eleventh article, R. Horio, N. Uchiyama, and S. Sano propose a human-operated biped robot for transporting objects over rough terrain or up steps. In the closing contribution, T. Sakuraba, N. Uchiyama, S. Sano, and T. Sakaguchi present the design of a spring-based regenerative brake, and they verify its effectiveness by driving a system that uses it.

We thank the referees for their comprehensive reviews and the staff members of Fuji Technology Press, Ltd. for their encouragement and advice.

It is our great pleasure to congratulate the Journal of Advanced Computational Intelligence and Intelligent Informatics (JACIII) on its 20^th anniversary. The concept of Computational Intelligence was originally authorized in the first IEEE World Congress on Computational Intelligence (WCCI) held in Orlando, Florida in 1994, where the key issues of CI were characterized by fuzzy, neuro, and EC (Evolutionary Computation). The JACI (Journal of Advanced Computational Intelligence) Vol.1 No.1 was published from Fuji Technology Press in Oct 1997, and the name of the journal has been changed to JACIII since Vol.7 No.1 Feb 2003 to accept more widely developed issues related to intelligent informatics.

The JACIII is currently published in bimonthly, six issues a year, in cooperation with International Fuzzy Systems Association (IFSA), Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT), Brazilian Society of Automatics (SBA), The Society of Instrument and Control Engineers (SICE), John von Neumann Computer Society (NJSZT), Vietnamese Fuzzy Systems Society (VFSS), Fuzzy Systems and Intelligent Technologies Research Society of Thailand (FIRST), Korean Institute of Intelligent Systems (KIIS), and Taiwanese Association for Artificial Intelligence (TAAI), and is indexed in ESCI, SCOPUS, and COMPENDEX (Ei-Index).

In the past 20 years personally, so many issues happened in the JACIII editing process. Some of them were very tough but all are very good memories to us. We occasionally organize the JACIII editorial meetings in Tokyo and remotely. As Editors-in-Chief, we are most grateful to all who have worked with the JACIII and helped reach its 20^th anniversary. We thank the editorial board members for editing this journal with their high discernment and the guest editors for arranging special issues with their high profession. We would also like to thank the peer reviewers for their accurate evaluations in a short time, and finally our special thanks go to the editorial office of Fuji Technology Press Ltd., especially to its founder, Mr. K. Hayashi, and to the editors, Ms. Reiko Ohta and Mr. Kunihiko Uchida for their efforts in publishing this journal.

First of all it is my great pleasure to congratulate to the 20^th anniversary of the Journal of Advanced Computational Intelligence and Intelligent Informatics (JACIII). The first volume of the journal was published in 1997 – and now twenty years later we reached the Vol. 21. Over these years JACIII was one of the forefront and determining journals of soft computing and intelligent informatics and focused to the most up-to-date topic despite the fast vary and evolvement of this research field through its regular and special sessions. One of the greatest merit of the journal is that it is able be serve as a common platform for the most relevant researchers and societies in order to expand the boundaries of many related fields including Fuzzy Logic, Neural Networks, Genetic and Evolutionary Computation, Biologically-Inspired Computation Systems and so on.

In these days the most up-coming challenges are connected to the topics of JACIII including the current special issue as well. Self-driving cars, Wearables, Internet-of-Things and many other phenomena are imaginable with the advanced Computational Intelligence behind the rooftop. Expert- and decision-making systems and effective usage of big data request the highly developed Fuzzy Inference Systems. Monitoring of social media in order to get useful information regarding the habits of human users and artificial robots cannot be realized without Web and Artificial Intelligence. Soft-computing based methods and many other intelligent and automated solutions are needed for eligible Data mining – and for the further preparation of the gathered data. Moreover, the demands of future smart city concepts, developed green energy producing solutions and connected power grids present the scientists with specific challenges whereon Smart Grid concept can be the only answer.

I would like to invite the Reader to an interesting reading which deals with the aforementioned challenges and scenarios.

Furthermore, I hope that JACIII can continue its contribution to the leading-edge research and we can celebrate the 30^th anniversary together as well.

It is my honour and privilege to express my heartfelt congratulations to the Journal of Advanced Computational Intelligence and Intelligent Informatics (JACIII) at the occasion of its 20^th Anniversary. I was so lucky to be one of the founding Advisory Editors in 1997, invited by two excellent researchers and very close friends, now Emeritus Professors Kaoru Hirota and Toshio Fukuda, and I have been on the board ever since. The journal covers all important fields of Computational Intelligence and Soft Computing including Fuzzy Systems, Artificial Neural Networks, Evolutionary Algorithms, and others. These areas emerged since the 1960-s, but especially since the second half of the 1980-s, when the Fuzzy Boom exploded in Japan. I was able to attend the International Fuzzy Systems Association World Congress in 1987 in Tokyo, in the same year when world’s first automatic subway line was opened in Sendai and when so many domotic and other applications appeared on the market, among other fuzzy and neuro-fuzzy commercial products. This was the occasion when I made the friendship of the two outstanding scholars, who later started JACIII.

From year to year I have diligently followed the articles published in JACIII, sending annually recommendations for the best paper awards, and occasionally sending papers for publication or advising my peers to support the journal. This way I can sincerely state that in the past 20 years JACIII has become one of the leading periodicals of the CI and SC fields, its authors distributed not only in Japan, but all over the world. At the beginning the focus was naturally on the fuzzy related papers, while in time the scope opened up towards all other related research fields, gradually covering all Intelligent Systems topics.

Why is the mentioned research area so important? Real life problems and many commercial applications, industrial, economic, bio-medical, environmental or others often pose a challenge by the complexity of the problem that disables modeling and algorithmic solutions from the mathematical point of view. This complexity partly comes from the large number of state variables describing the inputs and outputs involved with the model, or from the undeterministic nature, the high adaptability need, or simply from the involvement of subjective elements coming from human experts, operators or other persons. To all these mathematically intractable problem classes intelligent technologies often deliver a very good answer, a good compromise of resource efficiency and modeling “goodness”, i.e. approximation accuracy, or optimality error. The articles published in JACIII during the past 20 years have given many good answers to these challenging questions, offering new methodological results and new application technics.

I sincerely hope that JACIII will continue its fruitful and important activities and will play an ever increasing role in the international scenario of research publications on Intelligent Systems. Long live JACIII!

The JACIII was first published in 1997, and 2017 marks its 20^th anniversary. During the last two decades, the research fields in computational intelligence have rapidly evolved owing to the spread of the Internet, performance improvement of computers, and accumulation of scientific knowledge. To celebrate this 20^th anniversary, we have selected 6 important research areas from the JACIII scope, and invited outstanding researchers from each of these areas to contribute papers about the progress and major topics in those areas during the past 20 years. Submitted paper went through a peer-review process by distinguished professors to further improve the quality. The research areas selected were computational intelligence, fuzzy intelligence, intelligent robots, artificial intelligence and web intelligence, data mining, and smart grids. Each of those paper covers broad topics appeared in the research areas, from which readers could grasp what happened during the past 20 years. We also hope readers could find some hints about future directions of their own researches towards the next 20 years.

Invited Paper 1: Computational Intelligence: Retrospection and Future

Author: Witold Pedrycz (University of Alberta, Canada)

Invited Paper 2: Fuzzy Inference: Its Past and Prospects

Authors: Kiyohiko Uehara (Ibaraki University, Japan) and Kaoru Hirota (Beijing Institute of Technology, China)

Invited Paper 3: Relationship Between Human and Robot in Nonverbal Communication

Authors: Yukiko Nakagawa and Noriaki Nakagawa (RT Corporation, Japan)

Invited Paper 4: Web Intelligence and Artificial Intelligence

Author: Yasufumi Takama (Tokyo Metropolitan University, Japan)

Invited Paper 5: A Review of Data Mining Techniques and Applications

Authors: Ratchakoon Pruengkarn, Kok Wai Wong, and Chun Che Fung (Murdoch University, Australia)

Invited Paper 6: Development and Current State of Smart Grids: A Review

Author: Ken Nagasaka (Tokyo University of Agriculture and Technology, Japan)