Toshitaka Matsuki

According to our database, Toshitaka Matsuki authored at least 9 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Chaos-based reinforcement learning with TD3.

Toshitaka Matsuki, Yusuke Sakemi, Kazuyuki Aihara

CoRR, 2024

2023

Learning Reservoir Dynamics with Temporal Self-Modulation.

Yusuke Sakemi, Sou Nobukawa, Toshitaka Matsuki, Takashi Morie, Kazuyuki Aihara

CoRR, 2023

Data-driven Response Estimation-based Tuning and its Validation Using a Ball-and-Beam System.

Takao Sato, Yuta Sakai, Natsuki Kawaguchi, Masayoshi Hara, Toshitaka Matsuki, Masanori Takahashi, Orlando Arrieta, Ramón Vilanova

Proceedings of the 28th IEEE International Conference on Emerging Technologies and Factory Automation, 2023

2022

Deep Q-network using reservoir computing with multi-layered readout.

Toshitaka Matsuki

CoRR, 2022

2021

Sensitivity - Local index to control chaoticity or gradient globally -.

Katsunari Shibata, Takuya Ejima, Yuki Tokumaru, Toshitaka Matsuki

Neural Networks, 2021

2020

Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning.

Toshitaka Matsuki, Katsunari Shibata

Neural Networks, 2020

Q-learning with exploration driven by internal dynamics in chaotic neural network.

Toshitaka Matsuki, Souya Inoue, Katsunari Shibata

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

2017

Reinforcement Learning of a Memory Task Using an Echo State Network with Multi-layer Readout.

Toshitaka Matsuki, Katsunari Shibata

Proceedings of the Robot Intelligence Technology and Applications 5, 2017

2016

Reward-Based Learning of a Memory-Required Task Based on the Internal Dynamics of a Chaotic Neural Network.

Toshitaka Matsuki, Katsunari Shibata

Proceedings of the Neural Information Processing - 23rd International Conference, 2016