• ETRI Journal
• /
• v.43 no.6
• /
• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.1
• /
• pp.39-45
• /
• 2007

In this paper, we developed an intelligent web based e-learning system based on multi agents. To do development of the system, we applied an inclination test that is based on the education theory to do grouping the desirable e-learning community. The proposed system, Intelligent Web based e-learning Multi Agent System (IMAS), is used the multi agents paradigm including learning manner by neural network for grouping of e-learning community and a new distributed multi agent framework proposed here.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.51-58
• /
• 2009

Reinforcement learning is a sub area of machine learning concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In the case of multi-agent, especially, which state space and action space gets very enormous in compared to single agent, so it needs to take most effective measure available select the action strategy for effective reinforcement learning. This paper proposes a multi-agent reinforcement learning model based on fuzzy inference system in order to improve learning collect speed and select an effective action in multi-agent. This paper verifies an effective action select strategy through evaluation tests based on Robocup Keepaway which is one of useful test-beds for multi-agent. Our proposed model can apply to evaluate efficiency of the various intelligent multi-agents and also can apply to strategy and tactics of robot soccer system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.164.1-164
• /
• 2001

Q-learning is a recent reinforcement learning algorithm that does not need a modeling of environment and it is a suitable approach to learn behaviors for autonomous agents. But when it is applied to multi-agent learning with many I/O states, it is usually too complex and slow. To overcome this problem in the multi-agent learning system, we propose the successive Q-learning algorithm. Successive Q-learning algorithm divides state-action pairs, which agents can have, into several Q-functions, so it can reduce complexity and calculation amounts. This algorithm is suitable for multi-agent learning in a dynamically changing environment. The proposed successive Q-learning algorithm is applied to the prey-predator problem with the one-prey and two-predators, and its effectiveness is verified from the efficient avoidance ability of the prey agent.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.5
• /
• pp.49-57
• /
• 2008

In this paper, we suggested a methodology that can be used by an agent to learn models of other agents in a multi-agent system. To construct these model, we used influence diagram as a modeling tool. We present a method for learning models of the other agents at the decision nodes, value nodes, and chance nodes in influence diagram. We concentrated on learning of the other agents at the value node by using neural network learning technique. Furthermore, we treated anti-air units in anti-air defense domain as agents in multi. agent system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.187-193
• /
• 2013

In multi-agent systems, How to coordinate the behaviors of the agents through learning is a very important problem. The most important problems in the multi-agent system are to accomplish a goal through the efficient coordination of several agents and to prevent collision with other agents. In this paper, we propose a novel approach by using hybrid learning strategy. It is used hybrid learning strategy to control the multi-agent system efficiently by using the spatial relationship among the agents. Through experiments, we can see approximate faster the goal then other strategies and avoids collision among the agents.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• 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.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.587-594
• /
• 2001

Multi-agent system fits to the distributed and open internet environments. In a multi-agent system, agents must cooperate with each other through a coordination procedure, when the conflicts between agents arise. Where those are caused by the point that each action acts for a purpose separately without coordination. But previous researches for coordination methods in multi-agent system have a deficiency that they cannot solve correctly the cooperation problem between agents, which have different goals in dynamic environment. In this paper, we suggest the automatic coordination model for multi-agent system using neural network and reinforcement learning in dynamic environment. We have competitive experiment between multi-agents that have complexity environment and diverse activity. And we analysis and evaluate effect of activity of multi-agents. The results show that the proposed method is proper.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.292-297
• /
• 1999

Evolving in artificial agent is an extremely difficult problem, but on the other hand, a challenging task. At present the studies mainly centered on single agent learning problem. In our case, we use simulated soccer to investigate multi-agent cooperative learning. Consider the fundamental differences in learning mechanism, existing reinforcement learning algorithms can be roughly classified into two types-that based on evaluation functions and that of searching policy space directly. Genetic Programming developed from Genetic Algorithms is one of the most well known approaches belonging to the latter. In this paper, we give detailed algorithm description as well as data construction that are necessary for learning single agent strategies at first. In following step moreover, we will extend developed methods into multiple robot domains. game. We investigate and contrast two different methods-simple team learning and sub-group loaming and conclude the paper with some experimental results.