Multiagent Learning for Competitive Opinion Optimization
學年 111
學期 1
發表日期 2022-12-15
作品名稱 Multiagent Learning for Competitive Opinion Optimization
作品名稱（其他語言）
著者 Po-An Chen; Chi-Jen Lu; Chuang-Chieh Lin; Ke-Wei Fu
作品所屬單位
出版者
會議名稱 International Computer Symposium (ICS 2022)
會議地點 Taoyuan, Taiwan
摘要 From a perspective of designing or engineering for opinion formation games in social networks, the opinion maximization (or minimization) problem has been studied mainly for designing subset selecting algorithms. We define a two-player zero-sum Stackelberg game of competitive opinion optimization by letting the player under study as the leader minimize the sum of expressed opinions by doing so-called "internal opinion design", knowing that the other adversarial player as the follower is to maximize the same objective by also conducting her own internal opinion design. We furthermore consider multiagent learning, specifically using the Optimistic Gradient Descent Ascent, and analyze its convergence to equilibria in the simultaneous version of competitive opinion optimization.
關鍵字 Competitive opinion optimization;Multiagent learning;Optimistic Gradient Descent Ascent
語言 en
收錄於
會議性質 國際
校內研討會地點 無
研討會時間 20221215~20221217
通訊作者 Po-An Chen and Chuang-Chieh Lin
國別 TWN
公開徵稿
出版型式
出處 Proceedings of the 2022 International Computer Symposium (ICS 2022), Communications in Computer and Information Science (CCIS), Volume 1723
SDGS 優質教育