Within the framework of Multi-Agent Reinforcement Learning, Social Learning is a new class
of algorithms that enables agents to reshape the reward function of other agents with the …

对手建模作为多智能体博弈对抗的关键技术, 是一种典型的智能体认知行为建模方法.
介绍了多智能体博弈对抗几类典型模型, 非平稳问题和元博弈相关理论; 梳理总结对手建模方法 …

Differential games are a class of game theory problems governed by differential equations.
Differential games are often defined in the continuous domain and solved by the calculus of …

Behavioural cloning, where a computer is taught to perform a task based on demonstrations,
has been successfully applied to various video games and robotics tasks, with and without …

As the key technology of multi-agent game confrontation, opponent modeling is a typical
cognitive modeling method of agent's behavior. Several typical models of multi-agent game …

Artificial Intelligence is making rapid and remarkable progress in the development of more
sophisticated and powerful systems. However, the acknowledgement of several problems …

The Angry Birds AI competition has been held over many years to encourage the
development of AI agents that can play Angry Birds game levels better than human players …

In real-time strategy (RTS) games, the ability of recognizing other players' goals is important
for creating artifical intelligence (AI) players. However, most current goal recognition …

摘要深度强化学习是一种兼具深度学习特征提取能力和强化学习序列决策能力的智能体建模
方法, 能够弥补传统对手建模方法存在的非平稳性适应差, 特征选取复杂, 状态空间表示能力不足 …

Deception is essential to model real-world agent behaviors in entertainment and serious
games. This paper approaches the challenge of planning deceptive routes on topographic …