{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adaptation-to-criticality-through","title":"Adaptation to criticality through organizational invariance in embodied agents","arxiv_id":"1712.05284","date":"2017-12-13","proceeding":null,"authors":["Miguel Aguilera","Manuel G. Bedia"],"abstract":"Many biological and cognitive systems do not operate deep within one or other\nregime of activity. Instead, they are poised at critical points located at\nphase transitions in their parameter space. The pervasiveness of criticality\nsuggests that there may be general principles inducing this behaviour, yet\nthere is no well-founded theory for understanding how criticality is generated\nat a wide span of levels and contexts. In order to explore how criticality\nmight emerge from general adaptive mechanisms, we propose a simple learning\nrule that maintains an internal organizational structure from a specific family\nof systems at criticality. We implement the mechanism in artificial embodied\nagents controlled by a neural network maintaining a correlation structure\nrandomly sampled from an Ising model at critical temperature. Agents are\nevaluated in two classical reinforcement learning scenarios: the Mountain Car\nand the Acrobot double pendulum. In both cases the neural controller appears to\nreach a point of criticality, which coincides with a transition point between\ntwo regimes of the agent's behaviour. These results suggest that adaptation to\ncriticality could be used as a general adaptive mechanism in some\ncircumstances, providing an alternative explanation for the pervasive presence\nof criticality in biological and cognitive systems.","url_abs":"http://arxiv.org/abs/1712.05284v3","url_pdf":"http://arxiv.org/pdf/1712.05284v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adaptation-to-criticality-through","repo_url":"https://github.com/MiguelAguilera/Adaptation-to-criticality-through-organizational-invariance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"acrobot","task_name":"Acrobot"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}