• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.819-824
• /
• 1997

This paper presents a cell-based motion control strategy for soccer playing mobile robots. In the central robot motion planner, the planar ground is divided into rectangular cells with variable sizes and motion indices to which direction the mobile robot should move. At every time the multiple objects-the goal gate, ball, and robots-detected, integer values of motion indices are assigned to the cells occupied by mobile robots. Once the indices being calculated, the most desirable state-action pair is chosen from the state and action sets to achieve successful soccer game strategy. The proposed strategy is computationally simple enough to be used for fast robotic soccer system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.648-651
• /
• 1997

This paper proposes methods for the cooperative control of multiple mobile robots and constructs a robotic soccer system in which the cooperation will be implemented as a pass play of two robots. To play a soccer game, elementary actions such as shooting and moving have been designed, and Q-learning, which is one of the popular methods for reinforcement learning, is used to determine what actions to take. Through simulation, learning is successful in case of deliberate initial arrangements of ball and robots, thereby cooperative work can be accomplished.

• 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 ...

• 한국지능시스템학회논문지
• /
• 제12권4호
• /
• pp.289-293
• /
• 2002

분류자 시스템(Classifier System)은 유전자 알고리즘(Genetic Algorithmsm : GA)을 이용하여 새로운 규칙 집합을 발견하는 시스템이다 또 로봇 축구 시뮬레이션 게 (SimuroSot)은 시간에 따라 상태가 변화하는 동적인 시스템이다. 본 논문에서는 GBML(Genetic Based Machine Learning)의 한 갈래이자 미시간 접근 방법을 기반으로 하는 Zeroth Level Classifier System(ZCS)을 SimuroSot에 적용하여 게임 전략을 구성하는 새로운 규칙을 발견하고 학습하도록 하고 시뮬레이션 결과를 분석함으로써 ZCS의 유용성을 확인한다.

• 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.

• 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.

• 정보처리학회논문지B
• /
• 제9B권2호
• /
• pp.139-146
• /
• 2002

로봇 축구 시뮬레이션 게임은 하나의 동적 다중 에이전트 환경이다. 본 논문에서는 그러한 환경 하에서 각 에이전트의 동적 위치 결정을 위한 새로운 강화학습 방법을 제안한다. 강화학습은 한 에이전트가 환경으로부터 받는 간접적 지연 보상을 기초로 누적 보상값을 최대화할 수 있는 최적의 행동 전략을 학습하는 기계학습 방법이다. 따라서 강화학습은 입력-출력 쌍들이 훈련 예로 직접 제공되지 않는 다는 점에서 교사학습과 크게 다르다. 더욱이 Q-학습과 같은 비-모델 기반의 강화학습 알고리즘들은 주변 환경에 대한 어떤 모델도 학습하거나 미리 정의하는 것을 요구하지 않는다. 그럼에도 불구하고 이 알고리즘들은 에이전트가 모든 상태-행동 쌍들을 충분히 반복 경험할 수 있다면 최적의 행동전략에 수렴할 수 있다. 하지만 단순한 강화학습 방법들의 가장 큰 문제점은 너무 큰 상태 공간 때문에 보다 복잡한 환경들에 그대로 적용하기 어렵다는 것이다. 이런 문제점을 해결하기 위해 본 연구에서는 기존의 모듈화 Q-학습방법(MQL)을 개선한 적응적 중재에 기초한 모듈화 Q-학습 방법(AMMQL)을 제안한다. 종래의 단순한 모듈화 Q-학습 방법에서는 각 학습 모듈들의 결과를 결합하는 방식이 매우 단순하고 고정적이었으나 AMMQL학습 방법에서는 보상에 끼친 각 모듈의 기여도에 따라 모듈들에 서로 다른 가중치를 부여함으로써 보다 유연한 방식으로 각 모듈의 학습결과를 결합한다. 따라서 AMMQL 학습 방법은 큰 상태공간의 문제를 해결할 수 있을 뿐 아니라 동적인 환경변화에 보다 높은 적응성을 제공할 수 있다. 본 논문에서는 로봇 축구 에이전트의 동적 위치 결정을 위한 학습 방법으로 AMMQL 학습 방법을 사용하였고 이를 기초로 Cogitoniks 축구 에이전트 시스템을 구현하였다.