Search research articles

お問い合わせ

JoVEについて

概要リーダーシップブログ JoVEヘルプセンター

著者向け

出版プロセス編集委員会範囲と方針査読よくある質問投稿

図書館員向け

推薦の声購読アクセスリソース図書館諮問委員会よくある質問

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments アーカイブ

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教員リソースセンター教員サイト

プライバシーポリシー

関連する概念動画

Reinforcement

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

Collisions in Multiple Dimensions: Problem Solving

Collisions in Multiple Dimensions: Problem Solving

In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...

Reinforcement Schedules

Reinforcement Schedules

Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...

Associative Learning

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

Collisions in Multiple Dimensions: Introduction

Collisions in Multiple Dimensions: Introduction

It is far more common for collisions to occur in two dimensions; that is, the initial velocity vectors are neither parallel nor antiparallel to each other. Let's see what complications arise from this. The first idea is that momentum is a vector. Like all vectors, it can be expressed as a sum of perpendicular components (usually, though not always, an x-component and a y-component, and a z-component if necessary). Thus, when the statement of conservation of momentum is written for a...

こちらも読む

関連記事

共著者、ジャーナル、引用グラフによってこの研究に関連する記事。

並び替え

Same author

A Policy-Guided Reinforcement Learning Method for Encirclement Control in Multiobstacle Environment.

IEEE transactions on neural networks and learning systems·2025

Same author

An Adaptive Filter for Nonlinear Multi-Sensor Systems with Heavy-Tailed Noise.

Sensors (Basel, Switzerland)·2020

Same author

Monotonic regression: a new way for correlating subjective and objective ratings in image quality research.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2011

Same author

Enhancing the convergence efficiency of a self-propelled agent system via a weighted model.

Physical review. E, Statistical, nonlinear, and soft matter physics·2010

Search research articles

関連する実験動画

マルチエージェントの協力のためのグラフベースの安全な強化学習方法

Fandi Gou¹, Haikuo Du¹, Yunze Cai²

¹School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, 200240, China.

Neural networks : the official journal of the International Neural Network Society

|February 20, 2026

まとめ

この研究は,マルチエージェントシステムにおける安全性とスケーラビリティを改善するために,グラフベースの安全なマルチエージェント強化学習 (GS-MARL) を導入します. GS-MARLは,コミュニケーションが制限されたシナリオでのパフォーマンスを向上させ,既存の方法よりも高い成功率を達成します.

キーワード:

衝突回避法 (Collision Avoidance) は,衝突を回避するためのシステムである.制限された政策最適化.グラフニューラルネットワークマルチエージェントの協力安全な強化学習による安全学習です.

関連する実験動画

科学分野:

人工知能 (AI) とは,人工知能 (AI) のことです.
ロボット工学ロボット工学ロボット工学
コントロールシステムコントロールシステム

背景:

マルチエージェントシステム (MAS) は,安全性とコミュニケーションの課題に直面しています.
既存のマルチエージェント強化学習 (MARL) 方法は,報酬の形成と完全に接続されたコミュニケーションにより,安全性とスケーラビリティに問題があります.

研究の目的:

新しいフレームワーク,グラフベースのSafe MARL (GS-MARL) を提案し,MASのセキュリティとスケーラビリティを強化します.
現在のMARLアルゴリズムの限界を,実用的な応用で解決する.

主な方法:

MASの固有のグラフ構造をグラフニューラルネットワーク (GNN) でメッセージの伝送に活用する.
局所観測の下での安全性の向上のために,制限された共同政策最適化方法を実装する.

主要な成果:

GS-MARLは,既存の方法と比較して,最適性と安全性の間の優れたトレードオフを示しています.
大規模でコミュニケーションが制限されたシナリオでは少なくとも10%高い成功率を達成しました.
シミュレーション実験とMecanumの車輪付き車両のハードウェア実装を通じて検証されました.

結論:

GS-MARLは,MARLのセキュリティとスケーラビリティを効果的に強化しています.
このフレームワークは,ロボットシステムを含む現実世界のアプリケーションに実用的です.