部分可观测下循环智能体与脉冲智能体的预测性 allo-static 组织
Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability
浏览论文内容
中文总结 AI 辅助
该研究在部分可观测的能量受限觅食任务中，证实循环与脉冲智能体可发展出预测性、能量敏感的内部状态，其性能优于基线，为预测性 allo-static 组织提供计算类比。
中文摘要 AI 辅助
部分可观测下的适应性行为依赖于携带超出当前观测信息的内部组织。借鉴 Barrett 和 Miller 提出的分类是预测性、压缩性、功能组织化且受 allo-static 约束的观点，我们测试循环智能体与脉冲智能体是否发展出具有对应计算属性的内部状态。智能体在能量受限的觅食任务中运行，该任务要求获取资源、规避威胁、执行依赖接触的消耗并调节内部能量变量。在冻结基准中，学习得到的智能体性能优于随机和启发式基线；带迹增强的循环策略整体表现最佳，而脉冲变体在特定压力下表现出差异。早期内部动力学对后续完全安全高效的成功预测超过排列基线，达到最大 ROC-AUC 为 0.802。降维后的 PCA 子空间保留了与行为相关的信息。特征族控制实验显示，预测信号分布在迹、策略头、内部动力学、观测及 allo-static 变量中，且在移除显式能量相关特征后，低能量状态仍可被强解码。评估时对时间状态、感官信息、运行条件及 allo-static 机制的扰动会改变行为和/或内部预测。种子平衡事件探测显示，关于未来接触、成功消耗及威胁事件的信息较弱但可测量，同时低能量解码能力较强。我们将此模式解释为预测性 allo-static 组织的计算类比：分布式控制机制具有预测性、能量敏感性、与动作相关且部分参与因果过程，不主张其具有生物学验证或离散符号类别。
英文摘要
Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Barrett and Miller's account of categorization as predictive, compressive, functionally organized, and allostatically constrained, we test whether recurrent and spiking agents develop internal states with corresponding computational properties. Agents operate in an energy-constrained foraging task requiring resource acquisition, threat avoidance, contact-dependent consumption, and regulation of an internal energy variable. In a frozen benchmark, learned agents outperform random and heuristic baselines; the trace-augmented recurrent policy is strongest overall, while spiking variants show stress-specific differences. Early internal dynamics predict later full-safe-efficient success above permutation baseline, reaching a maximum ROC-AUC of 0.802. Reduced PCA subspaces retain behaviorally relevant information. Feature-family controls show that predictive signal is distributed across trace, policy-head, internal-dynamics, observation, and allostatic variables, and low-energy state remains strongly decodable after explicit energy-related features are removed. Evaluation-time perturbations to temporal state, sensory information, operating conditions, and allostatic mechanisms alter behavior and/or internal prediction. Seed-balanced event probes show weaker but measurable information about future contact, successful consumption, and threat events, alongside strong low-energy decoding. We interpret this pattern as a computational analogue of predictive allostatic organization: distributed control regimes that are predictive, energy-sensitive, action-relevant, and partly causally involved, without claiming biological validation or discrete symbolic categories.
