Search

Your search keyword '"Masuyama, Naoki"' showing total 39 results
Start Over Author "Masuyama, Naoki" Publisher ieee
39 results on '"Masuyama, Naoki"'

9. Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation

Author

Villin, Victor, Masuyama, Naoki, and Nojima, Yusuke

Subjects
FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing, Neural and Evolutionary Computing (cs.NE)
Abstract

Generating various strategies for a given task is challenging. However, it has already proven to bring many assets to the main learning process, such as improved behavior exploration. With the growth in the interest of heterogeneity in solution in evolutionary computation and reinforcement learning, many promising approaches have emerged. To better understand how one guides multiple policies toward distinct strategies and benefit from diversity, we need to analyze further the influence of the reward signal modulation and other evolutionary mechanisms on the obtained behaviors. To that effect, this paper considers an existing evolutionary reinforcement learning framework which exploits multi-objective optimization as a way to obtain policies that succeed at behavior-related tasks as well as completing the main goal. Experiments on the Atari games stress that optimization formulations which do not consider objectives equally fail at generating diversity and even output agents that are worse at solving the problem at hand, regardless of the obtained behaviors.

Published
2021

26. Handling Imbalance Between Convergence and Diversity in the Decision Space in Evolutionary Multimodal Multiobjective Optimization.

Author

Liu, Yiping, Ishibuchi, Hisao, Yen, Gary G., Nojima, Yusuke, and Masuyama, Naoki

Subjects
BENCHMARK problems (Computer science), SPACE, EVOLUTIONARY computation
Abstract

There may exist more than one Pareto optimal solution with the same objective vector to a multimodal multiobjective optimization problem (MMOP). The difficulties in finding such solutions can be different. Although a number of evolutionary multimodal multiobjective algorithms (EMMAs) have been proposed, they are unable to solve such an MMOP due to their convergence-first selection criteria. They quickly converge to the Pareto optimal solutions which are easy to find and therefore lose diversity in the decision space. That is, such an MMOP features an imbalance between achieving convergence and preserving diversity in the decision space. In this article, we first present a set of imbalanced distance minimization benchmark problems. Then we propose an evolutionary algorithm using a convergence-penalized density method (CPDEA). In CPDEA, the distances among solutions in the decision space are transformed based on their local convergence quality. Their density values are estimated based on the transformed distances and used as the selection criterion. We compare CPDEA with five state-of-the-art EMMAs on the proposed benchmarks. Our experimental results show that CPDEA is clearly superior in solving these problems. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

27. Adapting Reference Vectors and Scalarizing Functions by Growing Neural Gas to Handle Irregular Pareto Fronts.

Author

Liu, Yiping, Ishibuchi, Hisao, Masuyama, Naoki, and Nojima, Yusuke

Subjects
VECTOR valued functions, EVOLUTIONARY algorithms, EVOLUTIONARY computation, GASES, SEARCH algorithms
Abstract

The performance of decomposition-based multiobjective evolutionary algorithms (MOEAs) often deteriorates clearly when solving multiobjective optimization problems with irregular Pareto fronts (PFs). The main reason is the improper settings of reference vectors and scalarizing functions. In this paper, we propose a decomposition-based MOEA guided by a growing neural gas network, which learns the topological structure of the PF. Both reference vectors and scalarizing functions are adapted based on the topological structure to enhance the evolutionary algorithm’s search ability. The proposed algorithm is compared with eight state-of-the-art optimizers on 34 test problems. The experimental results demonstrate that the proposed method is competitive in handling irregular PFs. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

37. Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning.

Author

Masuyama, Naoki, Loo, Chu Kiong, Seera, Manjeevan, and Kubota, Naoyuki

Subjects
*COMPUTER science, *QUANTUM information theory, *ITERATIVE learning control, *QUANTUM mechanics, *EIGENVECTORS
Abstract

Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponential increase in storage capacity while explaining the extensive memory, and it has the potential to illustrate the dynamics of neurons in the human brain when viewed from quantum mechanics perspective although the application of QHAM is limited as an autoassociation. We introduce a quantum-inspired multidirectional associative memory (QMAM) with a one-shot learning model, and QMAM with a self-convergent iterative learning model (IQMAM) based on QHAM in this paper. The self-convergent iterative learning enables the network to progressively develop a resonance state, from inputs to outputs. The simulation experiments demonstrate the advantages of QMAM and IQMAM, especially the stability to recall reliability. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results