Using Graph-Aware Reinforcement Learning to Identify Winning Strategies in Diplomacy Games (Student Abstract)

被引:0
|
作者
Ahuja, Hansin [1 ]
Ng, Lynnette Hui Xian [2 ]
Jaidka, Kokil [3 ]
机构
[1] Indian Inst Technol Ropar, Rupnagar, Punjab, India
[2] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[3] Natl Univ Singapore, Singapore, Singapore
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This abstract proposes an approach towards goal-oriented modeling of the detection and modeling complex social phenomena in multiparty discourse in an online political strategy game. We developed a two-tier approach that first encodes sociolinguistic behavior as linguistic features then use reinforcement learning to estimate the advantage afforded to any player. In the first tier, sociolinguistic behavior, such as Friendship and Reasoning, that speakers use to influence others are encoded as linguistic features to identify the persuasive strategies applied by each player in simultaneous two-party dialogues. In the second tier, a reinforcement learning approach is used to estimate a graph-aware reward function to quantify the advantage afforded to each player based on their standing in this multiparty setup. We apply this technique to the game Diplomacy, using a dataset comprising of over 15,000 messages exchanged between 78 users. Our graph-aware approach shows robust performance compared to a context-agnostic setup.
引用
收藏
页码:12899 / 12900
页数:2
相关论文
共 15 条
  • [1] Efficient flow migration for NFV with Graph-aware deep reinforcement learning
    Sun, Penghao
    Lan, Julong
    Li, Junfei
    Guo, Zehua
    Hu, Yuxiang
    Hu, Tao
    [J]. COMPUTER NETWORKS, 2020, 183 (183)
  • [2] Reconfiguring multicast sessions in elastic optical networks adaptively with graph-aware deep reinforcement learning
    Tian, Xiaojian
    Li, Baojia
    Gu, Rentao
    Zhu, Zuqing
    [J]. JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING, 2021, 13 (11) : 253 - 265
  • [3] Selecting Portfolios Directly Using Recurrent Reinforcement Learning (Student Abstract)
    Li, Lin
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 13857 - 13858
  • [4] Solving JumpIN' Using Zero-Dependency Reinforcement Learning (Student Abstract)
    Ostic, Rachel
    Benning, Oliver
    Boily, Patrick
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 15861 - 15862
  • [5] Using Educational Data Mining to Identify and Analyze Student Learning Strategies
    Allen, Gove
    Davis, Randy
    Ball, Nicholas
    Albrecht, Conan
    Bakir, Nesrin
    [J]. PROCEEDINGS OF THE 52ND ANNUAL HAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES, 2019, : 13 - 21
  • [6] Using Reinforcement Learning for Operating Educational Campuses Safely during a Pandemic (Student Abstract)
    Ondula, Elizabeth Akinyi
    Krishnamachari, Bhaskar
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 13025 - 13026
  • [7] Determining the Possibility of Transfer Learning in Deep Reinforcement Learning Using Grad-CAM (Student Abstract)
    Joo, Ho-Taek
    Kim, Kyung-Joong
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 13831 - 13832
  • [8] Reward shaping using directed graph convolution neural networks for reinforcement learning and games
    Sang, Jianghui
    Ahmad Khan, Zaki
    Yin, Hengfu
    Wang, Yupeng
    [J]. FRONTIERS IN PHYSICS, 2023, 11
  • [9] Using cluster analysis to identify procrastination and student learning strategies in a flipped classroom
    Walsh, John N.
    [J]. INTERNATIONAL JOURNAL OF MANAGEMENT EDUCATION, 2024, 22 (01):
  • [10] Real-Time Coordination of Dynamic Network Reconfiguration and Volt-VAR Control in Active Distribution Network: A Graph-Aware Deep Reinforcement Learning Approach
    Wang, Ruoheng
    Bi, Xiaowen
    Bu, Siqi
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2024, 15 (03) : 3288 - 3302