{"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/criticality-as-it-could-be-organizational","title":"Criticality as It Could Be: organizational invariance as self-organized criticality in embodied agents","arxiv_id":"1704.05255","date":"2017-04-18","proceeding":null,"authors":["Miguel Aguilera","Manuel G. Bedia"],"abstract":"This paper outlines a methodological approach for designing adaptive agents\ndriving themselves near points of criticality. Using a synthetic approach we\nconstruct a conceptual model that, instead of specifying mechanistic\nrequirements to generate criticality, exploits the maintenance of an\norganizational structure capable of reproducing critical behavior. Our approach\nexploits the well-known principle of universality, which classifies critical\nphenomena inside a few universality classes of systems independently of their\nspecific mechanisms or topologies. In particular, we implement an artificial\nembodied agent controlled by a neural network maintaining a correlation\nstructure randomly sampled from a lattice Ising model at a critical point. We\nevaluate the agent in two classical reinforcement learning scenarios: the\nMountain Car benchmark and the Acrobot double pendulum, finding that in both\ncases the neural controller reaches a point of criticality, which coincides\nwith a transition point between two regimes of the agent's behaviour,\nmaximizing the mutual information between neurons and sensorimotor patterns.\nFinally, we discuss the possible applications of this synthetic approach to the\ncomprehension of deeper principles connected to the pervasive presence of\ncriticality in biological and cognitive systems.","url_abs":"http://arxiv.org/abs/1704.05255v3","url_pdf":"http://arxiv.org/pdf/1704.05255v3.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":"criticality-as-it-could-be-organizational","repo_url":"https://github.com/MiguelAguilera/Criticality-as-It-Could-Be","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"criticality-as-it-could-be-organizational","repo_url":"https://github.com/Osrip/CriticalCoEvolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"criticality-as-it-could-be-organizational","repo_url":"https://github.com/Osrip/CriticalEvolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"criticality-as-it-could-be-organizational","repo_url":"https://github.com/Osrip/evolution_dynamical_regime","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"criticality-as-it-could-be-organizational","repo_url":"https://github.com/heysoos/CriticalForagingOrgs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"criticality-as-it-could-be-organizational","repo_url":"https://github.com/heysoos/critical-ising-evolution","is_official":0,"mentioned_in_paper":0,"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}