• ETRI Journal
• /
• 제43권6호
• /
• pp.1004-1012
• /
• 2021

The collaboration productively interacting between multi-agents has become an emerging issue in real-world applications. In reinforcement learning, multi-agent environments present challenges beyond tractable issues in single-agent settings. This collaborative environment has the following highly complex attributes: sparse rewards for task completion, limited communications between each other, and only partial observations. In particular, adjustments in an agent's action policy result in a nonstationary environment from the other agent's perspective, which causes high variance in the learned policies and prevents the direct use of reinforcement learning approaches. Unexpected social loafing caused by high dispersion makes it difficult for all agents to succeed in collaborative tasks. Therefore, we address a paradox caused by the social loafing to significantly reduce total returns after a certain timestep of multi-agent reinforcement learning. We further demonstrate that the collaborative paradox in multi-agent environments can be avoided by our proposed effective early stop method leveraging a metric for social loafing.

• 한국콘텐츠학회논문지
• /
• 제9권10호
• /
• pp.51-58
• /
• 2009

강화학습은 최적의 행동정책을 구하는 최적화 문제로 주어진 환경과의 상호작용을 통해 받는 보상 값을 최대화하는 것이 목표이다. 특히 단일 에이전트에 비해 상태공간과 행동공간이 매우 커지는 다중 에이전트 시스템인 경우 효과적인 강화학습을 위해서는 적절한 행동 선택 전략이 마련되어야 한다. 본 논문에서는 멀티에이전트의 효과적인 행동 선택과 학습의 수렴속도를 개선하기 위하여 퍼지 추론 기반의 멀티에이전트 강화학습 모델을 제안하였다. 멀티 에이전트 강화학습의 대표적인 환경인 로보컵 Keepaway를 테스트 베드로 삼아 다양한 비교 실험을 전개하여 에이전트의 효율적인 행동 선택 전략을 확인하였다. 제안된 퍼지 추론 기반의 멀티에이전트 강화학습모델은 다양한 지능형 멀티 에이전트의 학습에서 행동 선택의 효율성 평가와 로봇축구 시스템의 전략 및 전술에 적용이 가능하다.

• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.9-17
• /
• 2021

동적 시스템 환경에서 지능형 협업 자율 시스템을 위한 기계학습 기반의 다양한 방법들이 연구 및 개발되고 있다. 본 연구에서는 분산 노드 기반 컴퓨팅 방식의 자율형 다중 에이전트 경로 탐색 방법을 제안하고 있으며, 지능형 학습을 통한 시스템 최적화를 위해 강화학습 방법을 적용하여 다양한 실험을 진행하였다. 강화학습 기반의 다중 에이전트 시스템은 에이전트의 연속된 행동에 따른 누적 보상을 평가하고 이를 학습하여 정책을 개선하는 지능형 최적화 기계학습 방법이다. 본 연구에서 제안한 방법은 강화학습 기반 다중 에이전트 최적화 경로 탐색 성능을 높이기 위해 학습 초기 경로 탐색 방법을 개선한 최적화 방법을 제안하고 있다. 또한, 분산된 다중 목표를 구성하여 에이전트간 정보 공유를 이용한 학습 최적화를 시도하였으며, 비동기식 에이전트 경로 탐색 기능을 추가하여 실제 분산 환경 시스템에서 일어날 수 있는 다양한 문제점 및 한계점에 대한 솔루션을 제안하고자 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.149.5-149
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent´s dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless ...

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.181-188
• /
• 2022

An intelligent distributed multi-agent system (IDMS) using reinforcement learning (RL) is a challenging and intricate problem in which single or multiple agent(s) aim to achieve their specific goals (sub-goal and final goal), where they move their states in a complex and cluttered environment. The environment provided by the IDMS provides a cumulative optimal reward for each action based on the policy of the learning process. Most actions involve interacting with a given IDMS environment; therefore, it can provide the following elements: a starting agent state, multiple obstacles, agent goals, and a cluttered index. The reward in the environment is also reflected by RL-based agents, in which agents can move randomly or intelligently to reach their respective goals, to improve the agent learning performance. We extend different cases of intelligent multi-agent systems from our previous works: (a) a proposed environment-clutter-based-index for agent sub-goal selection and analysis of its effect, and (b) a newly proposed RL reward scheme based on the environmental clutter-index to identify and analyze the prerequisites and conditions for improving the overall system.

• 한국공간구조학회논문집
• /
• 제23권2호
• /
• pp.29-36
• /
• 2023

Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• 한국멀티미디어학회논문지
• /
• 제6권5호
• /
• pp.937-944
• /
• 2003

다중 에이전트 시스템에서 가장 중요한 문제는 여러 에이전트가 서로 효율적인 협동(coordination)을 통해서 목표(goal)를 성취하는 것과 다른 에이전트들과의 충돌(collision) 을 방지하는 것이다. 본 논문에서는 먹이 추적 문제의 목표를 효율적으로 성취하기 위해 새로운 전략 방법을 제안한다. 제안된 제어 전략은 다중 에이전트를 제어하기 위해 강화 학습을 이용하였고, 에이전트들 간의 거리관계와 공간 관계를 고려하였다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.192-198
• /
• 2022

Companies are building and utilizing their own data analysis systems according to business characteristics in the distributed cloud. However, as businesses and data types become more complex and diverse, the demand for more efficient analytics has increased. In response to these demands, in this paper, we propose an unsupervised learning-based data analysis agent to which reinforcement learning is applied for effective data analysis. The proposal agent consists of reinforcement learning processing manager and unsupervised learning manager modules. These two modules configure an agent with k-means clustering on multiple nodes and then perform distributed training on multiple data sets. This enables data analysis in a relatively short time compared to conventional systems that perform analysis of large-scale data in one batch.