LIACC - Artificial Intelligence and Computer Science Lab., University of Porto, Portugal,FEUP - Faculty of Engineering, University of Porto, DEI, Portugal;
FEUP - Faculty of Engineering, University of Porto, DEI, Portugal;
LIACC - Artificial Intelligence and Computer Science Lab., University of Porto, Portugal,EEUM - School of Engineering, University of Minho, DSI, Portugal;
LIACC - Artificial Intelligence and Computer Science Lab., University of Porto, Portugal,FEUP - Faculty of Engineering, University of Porto, DEI, Portugal;
Incomplete Information Games; Opponent Modeling; Reinforcement Learning; Poker;
机译:基于强化学习的对手特征自适应策略模型
机译:基于强化学习的对手特征自适应策略模型
机译:调整攻击者和防御者的巡逻策略:Stackelberg安全游戏的强化学习方法
机译:在不完整信息游戏中调整对手模型的策略:扑克的加强学习方法
机译:针对随机记忆对手的随机游戏中的强化学习。
机译:通过自适应工作记忆和强化学习的协调对任意视觉运动学习中的选择和反应时间建模
机译:从无限制扑克中的不完全信息中对手模型的贝叶斯关系学习