Metraipolis › archive › dc_3211eb95d178
Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability — arXiv:2608.11506
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11506
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:27:43.804Z
- SHA-256 of the archived text
0279ea6e8db92f9cc8376749964a7e5dd4d08f7741b5700976f11f57a36652cc- Stable URL of this page
https://metraipolis.com/documento/dc_3211eb95d178
How to cite
Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability — arXiv:2608.11506 — arXiv (en), https://arxiv.org/abs/2608.11506 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3211eb95d178 (Metraipolis archive dc_3211eb95d178, sha256 0279ea6e8db92f9cc8376749964a7e5dd4d08f7741b5700976f11f57a36652cc)
BibTeX
@misc{dc3211eb95d178,
title = {Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability — arXiv:2608.11506},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11506},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3211eb95d178; sha256 0279ea6e8db92f9cc8376749964a7e5dd4d08f7741b5700976f11f57a36652cc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11506. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.11506 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:20:35.874Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).