Search Results for author: Takatomo Mihana

Found 9 papers, 0 papers with code

Asymmetric leader-laggard cluster synchronization for collective decision-making with laser network

no code implementations5 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.

Decision Making

Conflict-free joint decision by lag and zero-lag synchronization in laser network

no code implementations28 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.

Collision Avoidance Decision Making

Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk

no code implementations20 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.

Effect of temporal resolution on the reproduction of chaotic dynamics via reservoir computing

no code implementations27 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.

Time Series Time Series Prediction

Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation

no code implementations20 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.

Decision Making Multi-agent Reinforcement Learning +3

Parallel photonic accelerator for decision making using optical spatiotemporal chaos

no code implementations12 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.

Decision Making

Controlling chaotic itinerancy in laser dynamics for reinforcement learning

no code implementations12 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.

BIG-bench Machine Learning reinforcement-learning +1

Scalable photonic reinforcement learning by time-division multiplexing of laser chaos

no code implementations26 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.

Decision Making reinforcement-learning +3

Cannot find the paper you are looking for? You can Submit a new open access paper.