Toshiharu Sugawara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Toshiharu Sugawara has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
- Yuki Miyashita
Waseda University
12 shared publications Kensuke Fukuda
9 shared publicationsToshio Hirotsu
9 shared publications- Fujio Toriumi
School of Engineering, The University of Tokyo, Tokyo, Japan
8 shared publications - Kensuke Fukuda
National Institute of Informatics Tokyo Japan
6 shared publications Satoshi Kurihara
Institute of Scientific and Industrial Research, Osaka University, Osaka 567-0047, Japan
5 shared publications
Latest Publications
- Open Access
- 24 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 120-130
Deep Neural Network-guided PSO for Tracking a Global Optimal Position in Complex Dynamic Environment
- 24 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 120-130
Open AccessDeep Neural Network-guided PSO for Tracking a Global Optimal Position in Complex Dynamic Environment
- 25 February 2026
- Published by Springer Nature
- p. 242-253
The Backfire of Influence Operation: How Manipulating Moderate Influencers Affects Online Discourse
- 25 February 2026
- Published by Springer Nature
- p. 242-253
The Backfire of Influence Operation: How Manipulating Moderate Influencers Affects Online Discourse
- 1 February 2026
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 36 (2)
Robust and efficient communication in multi-agent reinforcement learning
Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.
- 1 February 2026
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 36 (2)
Robust and efficient communication in multi-agent reinforcement learning
Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.
- 24 November 2025
- Published by Springer Nature
- p. 92-104
Prioritized Path Planning for Multi-agent Pickup and Delivery with Multi-item Packing Problem
- 24 November 2025
- Published by Springer Nature
- p. 92-104
Prioritized Path Planning for Multi-agent Pickup and Delivery with Multi-item Packing Problem
- Open Access
Robust and Efficient Communication in Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.
Open AccessRobust and Efficient Communication in Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.
- 2 March 2025
- Published by Springer Nature
- p. 29-42
Fair Path Generation for Formation Control Combining Ant Colony and Particle Swarm Optimizations
- 2 March 2025
- Published by Springer Nature
- p. 29-42
Fair Path Generation for Formation Control Combining Ant Colony and Particle Swarm Optimizations
- 15 November 2024
- Published by Springer Nature
- p. 74-80
Path Finding with Flexible Provisional Booking in Multi-agent Pickup and Delivery Problems
- 15 November 2024
- Published by Springer Nature
- p. 74-80
Path Finding with Flexible Provisional Booking in Multi-agent Pickup and Delivery Problems
- Open Access
- 20 June 2024
- Published by Fuji Technology Press Ltd. in Journal of Robotics and Mechatronics
- Vol. 36 (3) , 658-668
Enhancing Multi-Agent Cooperation Through Action-Probability-Based Communication
Although communication plays a pivotal role in achieving coordinated activities in multi-agent systems, conventional approaches often involve complicated high-dimensional messages generated by deep networks. These messages are typically indecipherable to humans, are relatively costly to transmit, and require intricate encoding and decoding networks. This can pose a design limitation for the agents such as autonomous (mobile) robots. This lack of interpretability can lead to systemic issues with security and reliability. In this study, inspired by common human communication about likely actions in collaborative endeavors, we propose a novel approach in which each agent’s action probabilities are transmitted to other agents as messages, drawing inspiration from the common human practice of sharing likely actions in collaborative endeavors. Our proposed framework is referred to as communication based on action probabilities (CAP), and focuses on generating straightforward, low-dimensional, interpretable messages to support multiple agents in coordinating their activities to achieve specified cooperative goals. CAP streamlines our comprehension of the agents’ learned coordinated and cooperative behaviors and eliminates the need to use additional network models to generate messages. CAP’s network architecture is simpler than that of state-of-the-art methods, and our experimental results show that it nonetheless performed comparably, converged faster, and exhibited a lower volume of communication with better interpretability.
- 20 June 2024
- Published by Fuji Technology Press Ltd. in Journal of Robotics and Mechatronics
- Vol. 36 (3) , 658-668
Open AccessEnhancing Multi-Agent Cooperation Through Action-Probability-Based Communication
Although communication plays a pivotal role in achieving coordinated activities in multi-agent systems, conventional approaches often involve complicated high-dimensional messages generated by deep networks. These messages are typically indecipherable to humans, are relatively costly to transmit, and require intricate encoding and decoding networks. This can pose a design limitation for the agents such as autonomous (mobile) robots. This lack of interpretability can lead to systemic issues with security and reliability. In this study, inspired by common human communication about likely actions in collaborative endeavors, we propose a novel approach in which each agent’s action probabilities are transmitted to other agents as messages, drawing inspiration from the common human practice of sharing likely actions in collaborative endeavors. Our proposed framework is referred to as communication based on action probabilities (CAP), and focuses on generating straightforward, low-dimensional, interpretable messages to support multiple agents in coordinating their activities to achieve specified cooperative goals. CAP streamlines our comprehension of the agents’ learned coordinated and cooperative behaviors and eliminates the need to use additional network models to generate messages. CAP’s network architecture is simpler than that of state-of-the-art methods, and our experimental results show that it nonetheless performed comparably, converged faster, and exhibited a lower volume of communication with better interpretability.
- Open Access
- 14 May 2024
- Published by MDPI AG in Information
- Vol. 15 (5) , 279
Locally Centralized Execution for Less Redundant Computation in Multi-Agent Cooperation
Decentralized execution is a widely used framework in multi-agent reinforcement learning. However, it has a well-known but neglected shortcoming, redundant computation, that is, the same/similar computation is performed redundantly in different agents owing to their overlapping observations. This study proposes a novel method, the locally centralized team transformer (LCTT), to address this problem. This method first proposes a locally centralized execution framework that autonomously determines some agents as leaders that generate instructions and other agents as workers to act according to the received instructions without running their policy networks. For the LCTT, we subsequently propose the team-transformer (T-Trans) structure, which enables leaders to generate targeted instructions for each worker, and the leadership shift, which enables agents to determine those that should instruct or be instructed by others. The experimental results demonstrated that the proposed method significantly reduces redundant computations without decreasing rewards and achieves faster learning convergence.
- 14 May 2024
- Published by MDPI AG in Information
- Vol. 15 (5) , 279
Open AccessLocally Centralized Execution for Less Redundant Computation in Multi-Agent Cooperation
Decentralized execution is a widely used framework in multi-agent reinforcement learning. However, it has a well-known but neglected shortcoming, redundant computation, that is, the same/similar computation is performed redundantly in different agents owing to their overlapping observations. This study proposes a novel method, the locally centralized team transformer (LCTT), to address this problem. This method first proposes a locally centralized execution framework that autonomously determines some agents as leaders that generate instructions and other agents as workers to act according to the received instructions without running their policy networks. For the LCTT, we subsequently propose the team-transformer (T-Trans) structure, which enables leaders to generate targeted instructions for each worker, and the leadership shift, which enables agents to determine those that should instruct or be instructed by others. The experimental results demonstrated that the proposed method significantly reduces redundant computations without decreasing rewards and achieves faster learning convergence.
- Open Access
Reducing Redundant Computation in Multi-Agent Coordination through Locally Centralized Execution
In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the redundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to overlapping observations. To address this issue, this study introduces a novel method referred to as locally centralized team transformer (LCTT). LCTT establishes a locally centralized execution framework where selected agents serve as leaders, issuing instructions, while the rest agents, designated as workers, act as these instructions without activating their policy networks. For LCTT, we proposed the team-transformer (T-Trans) architecture that allows leaders to provide specific instructions to each worker, and the leadership shift mechanism that allows agents autonomously decide their roles as leaders or workers. Our experimental results demonstrate that the proposed method effectively reduces redundant computation, does not decrease reward levels, and leads to faster learning convergence.
Open AccessReducing Redundant Computation in Multi-Agent Coordination through Locally Centralized Execution
In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the redundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to overlapping observations. To address this issue, this study introduces a novel method referred to as locally centralized team transformer (LCTT). LCTT establishes a locally centralized execution framework where selected agents serve as leaders, issuing instructions, while the rest agents, designated as workers, act as these instructions without activating their policy networks. For LCTT, we proposed the team-transformer (T-Trans) architecture that allows leaders to provide specific instructions to each worker, and the leadership shift mechanism that allows agents autonomously decide their roles as leaders or workers. Our experimental results demonstrate that the proposed method effectively reduces redundant computation, does not decrease reward levels, and leads to faster learning convergence.