计算机应用研究
計算機應用研究
계산궤응용연구
APPLICATION RESEARCH OF COMPUTERS
2015年
5期
1335-1338,1344
,共5页
多 agent%自学习%RBF 神经网络%Q-强化学习%冲突消解
多 agent%自學習%RBF 神經網絡%Q-彊化學習%遲突消解
다 agent%자학습%RBF 신경망락%Q-강화학습%충돌소해
multi-agent%self-learning%RBF neural network%Q-reinforcement learning%conflict resolution
为提高传统协商自学习能力,利用多 agent 智能技术,建立基于黑板模型的协商框架,构建五元组协商模型,采取 Q-强化学习算法,给出一种协商策略;使用 RBF 神经网络进一步优化协商策略,预测对手信息并调整让步幅度。通过算例验证该方法的可行性和有效性,通过与未改进的 Q-强化学习算法对比,该方法可增强协商agent 的自学习能力,缩短协商时间,提高冲突消解效率。
為提高傳統協商自學習能力,利用多 agent 智能技術,建立基于黑闆模型的協商框架,構建五元組協商模型,採取 Q-彊化學習算法,給齣一種協商策略;使用 RBF 神經網絡進一步優化協商策略,預測對手信息併調整讓步幅度。通過算例驗證該方法的可行性和有效性,通過與未改進的 Q-彊化學習算法對比,該方法可增彊協商agent 的自學習能力,縮短協商時間,提高遲突消解效率。
위제고전통협상자학습능력,이용다 agent 지능기술,건립기우흑판모형적협상광가,구건오원조협상모형,채취 Q-강화학습산법,급출일충협상책략;사용 RBF 신경망락진일보우화협상책략,예측대수신식병조정양보폭도。통과산례험증해방법적가행성화유효성,통과여미개진적 Q-강화학습산법대비,해방법가증강협상agent 적자학습능력,축단협상시간,제고충돌소해효솔。
In order to improve the self-learning ability of traditional negotiation,this paper integrated multi-agent intelligent technology ,designed the negotiation framework based on the blackboard model,constructed the five-elements negotiation model,adopted the negotiation strategy based on Q-reinforcement learning,proposed a negotiation strategy;then it optimized the negotiation strategy by the RBF neural network,predicted the information of opponent for adjusting the concession extent. At last,it verifies the feasibility and validity of the algorithm through a sample application.When comparing to the un-opti-mized Q-reinforcement learning,it can enhance the learning ability of the negotiation agents,reduce the negotiation time,and improve the efficiency of resolving conflicts.