Takumi Aotani

Meiji University · Department of Mechanical Engineering Informatics

“Multi-agent systems (MAS)” have been extensively studied across various fields, including robotics, economics, biology, and computer science. A distinctive feature of these systems is the ability of multiple agents, each with different characteristics, to perform system-wide tasks through local bottom-up interactions. Furthermore, design and contr...

This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this parameterization has less expressiveness, it would fail to acquiring the optimal policy. A mixture model has capability of a...

Multi-Agent Reinforcement Learning (MARL) is a framework that utilizes reinforcement learning to simultaneously learn policies for multiple agents, such as robots, within the same environment. One concern with reinforcement learning is that stochastic behavior during learning can lead to risk for the agent. In the context of MARL, appropriately avo...

This paper describes an algorithm for determining the location of dishes in a dishwasher plate rack. We present an mathematical programming problem based on a rectangular packing problem in order to obtain a high packing density in a short period of time. Numerical simulations using a variety of tableware validate the effectiveness of the proposed...

Myoelectric prostheses are useful for improving the quality of life of amputees. Although current myoelectric analysis research has focused on increasing the number of identifiable grasp shapes, few studies have focused on estimating wrist posture. Therefore, in this study, we focus on the relationship between arm and wrist posture, and estimate th...

Model-based reinforcement learning is expected to be a method that can safely acquire the optimal policy under real-world conditions by using a stochastic dynamics model for planning. Since the stochastic dynamics model of the real world is generally unknown, a method for learning from state transition data is necessary. However, model learning suf...

A multi-agent system (MAS) is expected to be applied to various real-world problems where a single agent cannot accomplish given tasks. Due to the inherent complexity in the real-world MAS, however, manual design of group behaviors of agents is intractable. Multi-agent reinforcement learning (MARL), which is a framework for multiple agents in the s...

Multi-agent reinforcement learning (MARL) is a framework to make multiple agents (e.g., robots) in the same environment learn their policies simultaneously using reinforcement learning. In the conventional MARL, although decentralization is essential for feasible learning, rewards for the agents have been given from a centralized system (named as t...