物理具身的条件使泛化和关怀成为可能
The Conditions of Physical Embodiment Enable Generalization and Care
AI总结：
本文提出物理具身的条件是泛化和关怀的基础，通过稳态驱动和因果建模实现智能体在开放环境中的鲁棒性和可信对齐。
摘要：
随着人工智能体进入开放性的物理环境——如养老护理、灾难响应和太空任务——它们必须在不确定性中持续存在，同时提供可靠的照顾。然而，当前的系统在面对分布偏移时难以泛化，且缺乏内在动机来维护他人的福祉。脆弱性和死亡常被视为需要避免的限制，但生物体在开放世界中却能相对容易且高效地生存并提供照顾。我们主张泛化和关怀源于物理具身的条件：在世界中（智能体是环境的一部分）和朝向死亡（除非被抵消，智能体会趋向终端状态）。这些条件要求一种稳态驱动，以维持自身并最大化未来继续如此的能力。在多智能体环境中，长期时间跨度内满足这一驱动需要对自我和他人具身的稳健因果建模，以及可共同达成的未来状态。由于具身智能体是环境的一部分，其自我由可靠的控制所界定，赋能他人可以扩展自我边界，从而产生利他主义。这为从具身性向泛化和关怀的路径提供了基础，基于共享的约束。我们提出了一种强化学习框架来探讨这些问题。具有稳态死亡的智能体在开放性环境中持续学习，可能提供高效的稳健性和可信的对齐。
英文摘要：
As artificial agents enter open-ended physical environments -- eldercare, disaster response, and space missions -- they must persist under uncertainty while providing reliable care. Yet current systems struggle to generalize across distribution shifts and lack intrinsic motivation to preserve the well-being of others. Vulnerability and mortality are often seen as constraints to be avoided, yet organisms survive and provide care in an open-ended world with relative ease and efficiency. We argue that generalization and care arise from conditions of physical embodiment: being-in-the-world (the agent is a part of the environment) and being-towards-death (unless counteracted, the agent drifts toward terminal states). These conditions necessitate a homeostatic drive to maintain oneself and maximize the future capacity to continue doing so. Fulfilling this drive over long time horizons in multi-agent environments necessitates robust causal modeling of self and others' embodiment and jointly achievable future states. Because embodied agents are part of the environment, with the self delimited by reliable control, empowering others can expand self-boundaries, enabling other-regard. This provides a path from embodiment toward generalization and care based in shared constraints. We outline a reinforcement-learning framework for examining these questions. Homeostatic mortal agents continually learning in open-ended environments may offer efficient robustness and trustworthy alignment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
