no code implementations • 5 Dec 2023 • Shun Kotoku, Takatomo Mihana, André Röhm, Ryoichi Horisaki, Makoto Naruse
Photonic accelerators have recently attracted soaring interest, harnessing the ultimate nature of light for information processing.
no code implementations • 28 Jul 2023 • Hisako Ito, Takatomo Mihana, Ryoichi Horisaki, Makoto Naruse
In this study, we explore the application of a laser network, acting as a photonic accelerator, to the competitive multi-armed bandit problem.
no code implementations • 3 May 2023 • Honoka Shiratori, Hiroaki Shinkawa, André Röhm, Nicolas Chauvet, Etsuo Segawa, Jonathan Laurent, Guillaume Bachelier, Tomoki Yamagami, Ryoichi Horisaki, Makoto Naruse
Quantum processes can realize conflict-free joint decisions among two agents using the entanglement of photons or quantum interference of orbital angular momentum (OAM).
no code implementations • 20 Apr 2023 • Tomoki Yamagami, Etsuo Segawa, Takatomo Mihana, André Röhm, Ryoichi Horisaki, Makoto Naruse
Quantum walks (QWs) have a property that classical random walks (RWs) do not possess -- the coexistence of linear spreading and localization -- and this property is utilized to implement various kinds of applications.
no code implementations • 27 Jan 2023 • Kohei Tsuchiyama, André Röhm, Takatomo Mihana, Ryoichi Horisaki, Makoto Naruse
In recent years, reservoir computing has expanded to new functions such as the autonomous generation of chaotic time series, as well as time series prediction and classification.
no code implementations • 20 Dec 2022 • Hiroaki Shinkawa, Nicolas Chauvet, André Röhm, Takatomo Mihana, Ryoichi Horisaki, Guillaume Bachelier, Makoto Naruse
In addition, we propose a multi-agent architecture in which agents are indirectly connected through quantum interference of light and quantum principles ensure the conflict-free property of state-action pair selections among agents.
no code implementations • 12 Oct 2022 • Kensei Morijiri, Kento Takehana, Takatomo Mihana, Kazutaka Kanno, Makoto Naruse, Atsushi Uchida
We solve a 512-armed bandit problem online, which is much larger than previous experiments by two orders of magnitude.
no code implementations • 5 Aug 2022 • Hiroaki Shinkawa, Nicolas Chauvet, André Röhm, Takatomo Mihana, Ryoichi Horisaki, Guillaume Bachelier, Makoto Naruse
Second, to derive the optimal joint selection probability matrix, all players must disclose their probabilistic preferences.
no code implementations • 19 May 2022 • Takashi Urushibara, Nicolas Chauvet, Satoshi Kochi, Satoshi Sunada, Kazutaka Kanno, Atsushi Uchida, Ryoichi Horisaki, Makoto Naruse
Q-learning is a well-known approach in reinforcement learning that can deal with many states.
no code implementations • 12 May 2022 • Ryugo Iwami, Takatomo Mihana, Kazutaka Kanno, Satoshi Sunada, Makoto Naruse, Atsushi Uchida
In this paper, we propose a method for controlling the chaotic itinerancy in a multi-mode semiconductor laser to solve a machine learning task, known as the multi-armed bandit problem, which is fundamental to reinforcement learning.
no code implementations • 2 May 2022 • Hiroaki Shinkawa, Nicolas Chauvet, Guillaume Bachelier, André Röhm, Ryoichi Horisaki, Makoto Naruse
Here, we theoretically derive conflict-free joint decision-making that can satisfy the probabilistic preferences of all individual players.
no code implementations • 30 Mar 2022 • Norihiro Okada, Tomoki Yamagami, Nicolas Chauvet, Yusuke Ito, Mikio Hasegawa, Makoto Naruse
In this study, we demonstrate a theoretical model to account for accelerating decision-making by correlated time sequence.
no code implementations • 17 Jan 2022 • Hideyuki Muneta, Ryoichi Horisaki, Yohei Nishizaki, Makoto Naruse, Jun Tanida
In this paper, we present a method for single-shot blind deconvolution incorporating a coded aperture (CA).
no code implementations • 2 Jul 2021 • Takashi Amakasu, Nicolas Chauvet, Guillaume Bachelier, Serge Huant, Ryoichi Horisaki, Makoto Naruse
In recent cross-disciplinary studies involving both optics and computing, single-photon-based decision-making has been demonstrated by utilizing the wave-particle duality of light to solve multi-armed bandit problems.
no code implementations • 26 May 2020 • Naoki Narisawa, Nicolas Chauvet, Mikio Hasegawa, Makoto Naruse
By exploiting ultrafast and irregular time series generated by lasers with delayed feedback, we have previously demonstrated a scalable algorithm to solve multi-armed bandit (MAB) problems utilizing the time-division multiplexing of laser chaos time series.
no code implementations • 27 Apr 2020 • Kazutaka Kanno, Makoto Naruse, Atsushi Uchida
Here, we propose a scheme of adaptive model selection in photonic reservoir computing using reinforcement learning.
no code implementations • 29 Jul 2019 • Tomoaki Niiyama, Genki Furuhata, Atsushi Uchida, Makoto Naruse, Satoshi Sunada
Decision making is a fundamental capability of living organisms, and has recently been gaining increasing importance in many engineering applications.
no code implementations • 24 May 2019 • Makoto Naruse, Takashi Matsubara, Nicolas Chauvet, Kazutaka Kanno, Tianyu Yang, Atsushi Uchida
Here we utilize chaotic time series generated experimentally by semiconductor lasers for the latent variables of GAN whereby the inherent nature of chaos can be reflected or transformed into the generated output data.
no code implementations • 12 Apr 2018 • Nicolas Chauvet, David Jegouso, Benoît Boulanger, Hayato Saigo, Kazuya Okamura, Hirokazu Hori, Aurélien Drezet, Serge Huant, Guillaume Bachelier, Makoto Naruse
The competitive multi-armed bandit (CMAB) problem is related to social issues such as maximizing total social benefits while preserving equality among individuals by overcoming conflicts between individual decisions, which could seriously decrease social benefits.
no code implementations • 12 Apr 2018 • Makoto Naruse, Eiji Yamamoto, Takashi Nakao, Takuma Akimoto, Hayato Saigo, Kazuya Okamura, Izumi Ojima, Georg Northoff, Hirokazu Hori
Our proposed model is inspired by the viewpoint that a decision is affected by its local environment, which is referred to as a local reservoir.
no code implementations • 26 Mar 2018 • Makoto Naruse, Takatomo Mihana, Hirokazu Hori, Hayato Saigo, Kazuya Okamura, Mikio Hasegawa, Atsushi Uchida
In this study, we demonstrated a scalable, pipelined principle of resolving the multi-armed bandit problem by introducing time-division multiplexing of chaotically oscillated ultrafast time-series.
no code implementations • 14 Apr 2017 • Makoto Naruse, Yuta Terashima, Atsushi Uchida, Song-Ju Kim
Reinforcement learning involves decision making in dynamic and uncertain environments, and constitutes one important element of artificial intelligence (AI).
no code implementations • 1 Sep 2016 • Makoto Naruse, Martin Berthel, Aurélien Drezet, Serge Huant, Hirokazu Hori, Song-Ju Kim
In a past study, we successfully used the wave-particle duality of single photons to solve the two-armed bandit problem, which constitutes the foundation of reinforcement learning and decision making.
no code implementations • 26 Feb 2016 • Makoto Naruse, Song-Ju Kim, Masashi Aono, Martin Berthel, Aurélien Drezet, Serge Huant, Hirokazu Hori
Decision making is a vital function in this age of machine learning and artificial intelligence, yet its physical realization and theoretical fundamentals are still not completely understood.
no code implementations • 14 Apr 2015 • Song-Ju Kim, Makoto Naruse, Masashi Aono
Our society comprises a collection of such individuals, and the society is expected to maximise the total rewards, while the individuals compete for common rewards.