Toshitaka Matsuki

13 papers B 1C 1Journal 9Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Chaos-based reinforcement learning with TD3. Neural Networks Toshitaka Matsuki, Yusuke Sakemi, Kazuyuki Aihara
2026	J	`jnl`	Uncovering Latent Phase Structures and Branching Logic in Locomotion Policies: A Case Study on HalfCheetah. CoRR Daisuke Yasui, Toshitaka Matsuki, Hiroshi Sato
2025	J	`jnl`	Dynamic LRP-Based Pruning for CNNs in Data-Scarce Transfer Learning: Suppressing Cascading Accuracy Degradation. CoRR Daisuke Yasui, Toshitaka Matsuki, Hiroshi Sato
2024	J	`jnl`	Chaos-based reinforcement learning with TD3. CoRR Toshitaka Matsuki, Yusuke Sakemi, Kazuyuki Aihara
2023	C	`conf`	Data-driven Response Estimation-based Tuning and its Validation Using a Ball-and-Beam System. ETFA Takao Sato, Yuta Sakai, Natsuki Kawaguchi, Masayoshi Hara, Toshitaka Matsuki, Masanori Takahashi, Orlando Arrieta, Ramón Vilanova
2023	J	`jnl`	Learning Reservoir Dynamics with Temporal Self-Modulation. CoRR Yusuke Sakemi, Sou Nobukawa, Toshitaka Matsuki, Takashi Morie, Kazuyuki Aihara
2022	J	`jnl`	Deep Q-network using reservoir computing with multi-layered readout. CoRR Toshitaka Matsuki
2021	J	`jnl`	Sensitivity - Local index to control chaoticity or gradient globally -. Neural Networks Katsunari Shibata, Takuya Ejima, Yuki Tokumaru, Toshitaka Matsuki
2020	J	`jnl`	Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning. Neural Networks Toshitaka Matsuki, Katsunari Shibata
2020	B	`conf`	Q-learning with exploration driven by internal dynamics in chaotic neural network. IJCNN Toshitaka Matsuki, Souya Inoue, Katsunari Shibata
2020	J	`jnl`	Sensitivity - Local Index to Control Chaoticity or Gradient Globally. CoRR Katsunari Shibata, Takuya Ejima, Yuki Tokumaru, Toshitaka Matsuki
2017	—	`conf`	Reinforcement Learning of a Memory Task Using an Echo State Network with Multi-layer Readout. RiTA Toshitaka Matsuki, Katsunari Shibata
2016	—	`conf`	Reward-Based Learning of a Memory-Required Task Based on the Internal Dynamics of a Chaotic Neural Network. ICONIP (1) Toshitaka Matsuki, Katsunari Shibata