Deception in social learning: A multi-agent reinforcement learning perspective
P Chelarescu - arXiv preprint arXiv:2106.05402, 2021 - arxiv.org
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 …
of algorithms that enables agents to reshape the reward function of other agents with the …
面向多智能体博弈对抗的对手建模框架
罗俊仁, 张万鹏, 袁唯淋, 胡振震, 陈少飞… - 系统仿真学报, 2022 - china-simulation.com
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 …
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 …
Learning deception using fuzzy multi-level reinforcement learning in a multi-defender one-invader differential game
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 …
Differential games are often defined in the continuous domain and solved by the calculus of …
Benchmarking end-to-end behavioural cloning on video games
A Kanervisto, J Pussinen… - 2020 IEEE conference on …, 2020 - ieeexplore.ieee.org
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 …
has been successfully applied to various video games and robotics tasks, with and without …
Research on opponent modeling framework for multi-agent game confrontation
J Luo, W Zhang, W Yuan, Z Hu… - Journal of …, 2022 - dc-china-simulation …
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 …
cognitive modeling method of agent's behavior. Several typical models of multi-agent game …
Direct human-AI comparison in the animal-AI environment
Artificial Intelligence is making rapid and remarkable progress in the development of more
sophisticated and powerful systems. However, the acknowledgement of several problems …
sophisticated and powerful systems. However, the acknowledgement of several problems …
Deceptive level generation for angry birds
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 …
development of AI agents that can play Angry Birds game levels better than human players …
Recognition and interfere deceptive behavior based on inverse reinforcement learning and game theory
Y Zeng, K Xu - Journal of Systems Engineering and Electronics, 2023 - ieeexplore.ieee.org
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 …
for creating artifical intelligence (AI) players. However, most current goal recognition …
基于深度强化学习的对手建模方法研究综述
徐浩添, 秦龙, 曾俊杰, 胡越, 张琪 - 系统仿真学报, 2023 - china-simulation.com
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 …
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 …
Deceptive Topographic Path Planning
C Lenhard, HL Krever, RK Schlsener… - Proceedings of the …, 2023 - dl.acm.org
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 …
games. This paper approaches the challenge of planning deceptive routes on topographic …