Simulation is widely used to make model-based predictions, but few approaches have attempted this technique in dynamic physical environments of medium to high complexity or in general contexts. After an introduction to the cognitive science concepts from which this work is inspired and the current development in the use of simulation as a decision-making technique, we propose a generic framework based on theory of mind, which allows an agent to reason and perform actions using multiple simulations of automatically created or externally inputted models of the perceived environment. A description of a partial implementation is given, which aims to solve a popular game within the IJCAI2013 AIBirds contest. Results of our approach are presented, in comparison with the competition benchmark. Finally, future developments regarding the framework are discussed.
CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
BrainCog Lab, Institute of Automation, Chinese Academy of Sciences(脑认知实验室,自动化研究所,中国科学院);Beijing Institute of AI Safety and Governance (Beijing-AISI)(北京人工智能安全与治理研究所);Beijing Key Laboratory of Safe AI and Superalignment(北京安全人工智能与超对齐重点实验室);School of Artificial Intelligence, UCAS(人工智能学院,中国科学院大学);Long-term AI(长期人工智能)
Emergence of Theory of Mind Collaboration in Multiagent Systems
University of California, Los Angeles(加利福尼亚大学洛杉矶分校)
目前,在多智能体系统的研究中,往往忽略了智能体的意图。尽管如此,正如心理理论(Theory of Mind,ToM)所指出的,人们经常会对他人的心理状态进行推理,包括信念、目标和意图,以在竞争、合作或联盟中获得绩效优势。然而,由于其固有的递归性和难以建模的分布信念,集成ToM的多智能体规划和决策仍然是一个挑战。在本文中,我们将ToM在多智能体部分可观察马尔可夫决策过程(POMDP),并提出了一个自适应训练算法,开发有效的合作与ToM代理。我们用两个游戏来评估我们的算法,我们的算法超过了以前所有的分散执行算法,而没有对ToM进行建模。
Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning
Hebrew University of Jerusalem(海法大学);MPI for Biological Cybernetics(生物感知研究所);Centre for AI and Machine Learning, AU(人工智能与机器学习中心);IoPPN, King’s College London(国王学院伦敦人工智能与感知神经科学中心)
Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
School of EEE, Nanyang Technological University(南洋理工大学电子工程系);Department of Civil Engineering, Tsinghua University(清华大学土木工程系);Dr. B. R. Ambedkar National Institute of Technology, Jalandhar(B.R.阿姆贝卡尔国家理工学院,贾兰德赫);KTH Royal Institute of Technology(皇家理工学院);College of AI, Tsinghua University(清华大学人工智能学院);CCDS, Nanyang Technological University(南洋理工大学CCDS)
Towards Anthropo-inspired Computational Systems: the $P^3$ Model
iCarnegie Global Learning(iCarnegie全球学习);Politecnico di Milano(米兰理工大学);Kazan Federal University(喀山联邦大学);Innopolis University(Innopolis大学);Institut de Neurobiologie de la Méditerranée(地中海神经生物学研究所);Aix-Marseille University(艾克斯-马赛大学);Universitat Autònoma de Barcelona(巴塞罗那自治大学)
Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy
University of Essex(埃塞克斯大学);Università degli Studi di Milano Bicocca(米兰比可卡大学)
在复杂的环境中,人类的感觉系统达到了极限,我们的行为受到我们对周围世界状态的信念的强烈驱动。因此,在自然环境中,理解他人的信仰、意图或一般的精神状态,可以实现更有效的社会互动。然而,这些变量并不能直接观察到。心理理论(英语:Theory of Mind,简称TOM)是一种将其他智能体的信念、意图或精神状态归因于其他智能体的能力,是人类社会互动的一个重要特征,也是机器人社区感兴趣的领域。最近,已经引入了能够学习TOM的新模型。在本文中,我们展示了学习预测低层次心理状态(如意图和目标)与归因于高层次心理状态(如信念)之间的协同作用。假设信念的学习可以通过在部分可观察的环境中观察自己的决策和信念估计过程并使用简单的前馈深度学习模型来进行,我们表明,当学习预测他人的意图和行动时,如果信念归因与行动和意图预测同时学习,则可以获得更快,更准确的预测。我们表明,学习性能提高,即使在观察代理与不同的决策过程,是更高的观察时,信念驱动的块的行为。我们建议,我们的架构方法可以为未来的自适应社会机器人,应该能够自主理解和协助人类合作伙伴在新的自然环境和任务的设计相关。
The Hive Mind is a Single Reinforcement Learning Agent
MIST Lab, Department of Computer and Software Engineering(MIST实验室,计算机与软件工程系);Polytechnique Montréal(蒙特利尔大学);Mila - Quebec AI Institute(魁北克人工智能研究所);Department of Computer and Information Science(计算机与信息科学系);University of Konstanz(康斯坦茨大学)