Playout Policy Adaptation for Games

被引:7
|
作者
Cazenave, Tristan [1 ]
机构
[1] Univ Paris 09, LAMSADE, Paris, France
来源
关键词
D O I
10.1007/978-3-319-27992-3_3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Monte-Carlo Tree Search (MCTS) is the state of the art algorithm for General Game Playing (GGP). We propose to learn a playout policy online so as to improve MCTS for GGP. We test the resulting algorithm named Playout Policy Adaptation (PPA) on Atarigo, Breakthrough, Misere Breakthrough, Domineering, Misere Dominee-ring, Go, Knightthrough, Misere Knightthrough, Nogo and Misere Nogo. For most of these games, PPA is better than UCT with a uniform random playout policy, with the notable exceptions of Go and Nogo.
引用
收藏
页码:20 / 28
页数:9
相关论文
共 50 条
  • [1] Playout policy adaptation with move features
    Cazenave, Tristan
    THEORETICAL COMPUTER SCIENCE, 2016, 644 : 43 - 52
  • [2] Memorizing the Playout Policy
    Cazenave, Tristan
    Diemert, Eustache
    COMPUTER GAMES (CGW 2017), 2018, 818 : 96 - 107
  • [3] Interactivity-Aware Playout Adaptation
    Issing, Jochen
    Faerber, Nikolaus
    German, Reinhard
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 428 - 432
  • [4] Predictive playout delay adaptation for Voice over Internet
    Matic, V
    Bazant, A
    Kos, M
    MELECON 2000: INFORMATION TECHNOLOGY AND ELECTROTECHNOLOGY FOR THE MEDITERRANEAN COUNTRIES, VOLS 1-3, PROCEEDINGS, 2000, : 348 - 351
  • [5] Cheat-proof playout for centralized and distributed online games
    Baughman, NE
    Levine, BN
    IEEE INFOCOM 2001: THE CONFERENCE ON COMPUTER COMMUNICATIONS, VOLS 1-3, PROCEEDINGS: TWENTY YEARS INTO THE COMMUNICATIONS ODYSSEY, 2001, : 104 - 113
  • [6] Conservative Offline Policy Adaptation in Multi-Agent Games
    Wu, Chengjie
    Tang, Pingzhong
    Yang, Jun
    Hu, Yujing
    Lv, Tangjie
    Fan, Changjie
    Zhang, Chongjie
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [7] Neural and fuzzy computation techniques for playout delay adaptation in VoIP networks
    Ranganathan, MK
    Kilmartin, L
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (05): : 1174 - 1194
  • [8] Cross-level linkages in an ecology of climate change adaptation policy games
    Hamilton, Matthew
    Lubell, Mark
    Namaganda, Emilinah
    ECOLOGY AND SOCIETY, 2018, 23 (02):
  • [9] Games with Adaptation and Mitigation
    Hritonenko, Natali
    Hritonenko, Victoria
    Yatsenko, Yuri
    GAMES, 2020, 11 (04): : 1 - 16
  • [10] Packet scheduling with playout adaptation for scalable video delivery over wireless networks
    Hung, Tzu-Yi
    Chen, Zhenzhong
    Tan, Yap-Peng
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2011, 22 (06) : 491 - 503