KJCKorea
Journal Central

@article{ART002021677},
author={이봉근 and Ahn, Yoon-ae},
title={An Action Select Reinforcement Learning Model in Multi Agent Environment},
journal={Journal of Knowledge Information Technology and Systems},
issn={1975-7700},
year={2015},
volume={10},
number={4},
pages={455-463}

TY - JOUR
AU - 이봉근
AU - Ahn, Yoon-ae
TI - An Action Select Reinforcement Learning Model in Multi Agent Environment
JO - Journal of Knowledge Information Technology and Systems
PY - 2015
VL - 10
IS - 4
PB - Korea Knowledge Information Technology Society
SP - 455
EP - 463
SN - 1975-7700
AB - Reinforcement learning is concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In particular, a multi-agent system consisting of multiple interacting agents has increased state and action space as compared to a single agent system, so it must have an effective action selection mechanism. Reinforcement learning is used to evaluate and improve the effectiveness of a robotic soccer agent's action selection. That is, an agent that chooses its actions according to a certain action selection policy receives feedback regarding whether the chosen actions are desirable or not, and the agent learns to find optimal actions for various states in simulated soccer games based on the feedback. Possible states were identified by analyzing various situations/conditions arising in simulated soccer games, and then action selection policies were defined based on the analysis of a soccer agent's behavior patterns. In this paper can be exploited to develop optimized strategies and tactics for robot soccer systems, and it is also applicable to other multi-agent learning environments similar to the robot soccer game environment. In such environments, it is significant to acquire a policy that enables intelligent agents to work cooperatively to win the game.
KW - Multi-agent;Reinforcement Learning;Optimal actions;ε-greedy;Robocup
DO -
UR -
ER -

이봉근 and Ahn, Yoon-ae. (2015). An Action Select Reinforcement Learning Model in Multi Agent Environment. Journal of Knowledge Information Technology and Systems, 10(4), 455-463.

이봉근 and Ahn, Yoon-ae. 2015, "An Action Select Reinforcement Learning Model in Multi Agent Environment", Journal of Knowledge Information Technology and Systems, vol.10, no.4 pp.455-463.

이봉근, Ahn, Yoon-ae "An Action Select Reinforcement Learning Model in Multi Agent Environment" Journal of Knowledge Information Technology and Systems 10.4 pp.455-463 (2015) : 455.

이봉근, Ahn, Yoon-ae. An Action Select Reinforcement Learning Model in Multi Agent Environment. 2015; 10(4), 455-463.

이봉근 and Ahn, Yoon-ae. "An Action Select Reinforcement Learning Model in Multi Agent Environment" Journal of Knowledge Information Technology and Systems 10, no.4 (2015) : 455-463.

이봉근; Ahn, Yoon-ae. An Action Select Reinforcement Learning Model in Multi Agent Environment. Journal of Knowledge Information Technology and Systems, 10(4), 455-463.

이봉근; Ahn, Yoon-ae. An Action Select Reinforcement Learning Model in Multi Agent Environment. Journal of Knowledge Information Technology and Systems. 2015; 10(4) 455-463.

이봉근, Ahn, Yoon-ae. An Action Select Reinforcement Learning Model in Multi Agent Environment. 2015; 10(4), 455-463.

이봉근 and Ahn, Yoon-ae. "An Action Select Reinforcement Learning Model in Multi Agent Environment" Journal of Knowledge Information Technology and Systems 10, no.4 (2015) : 455-463.