Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light

[2507.11482] Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light Skip to main content Search Submit Donate Log in Computer Science > Artificial Intelligence arXiv:2507.11482 (cs) [Submitted on 15 Jul 2025 ( v1 ), last revised 24 Aug 2026 (this version, v5)] Title: Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light Authors: Mani Hamidi , Terrence W. Deacon View PDF HTML (experimental) Abstract: Artificial learning systems are graduating from passive learners to increasingly autonomous agents, lending pragmatic urgency to the question of what constitutes agency. Reinforcement learning (RL) offers arguably the most explicit formulation of agent-environment interaction, built on three core tenets: the environment as a Markov decision process, learning as policy optimization, and the agent as a maximizer of scalar reward. Recent work has called to revise these tenets: reconceptualizing learning as adaptation rather than optimization, broadening goals beyond scalar reward, and noting the absence of a formal theory of the agent in a formalism that so heavily emphasizes the environment. We argue that the artificial life community is uniquely positioned to illuminate this critique and concretize an alternative. We draw on open-ended novelty search as a complementary model of adaptation and goal-directed behavior beyond reward optimization, and ground such evolutionary dynamics in thermodynamic theories of origin-of-life and agency, toward a more biologically faithful and formally grounded account of what it is to be an adaptive agent. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2507.11482 [cs.AI] (or arXiv:2507.11482v5 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2507.11482 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Mani Hamidi [ view email ] [v1] Tue, 15 Jul 2025 16:53:14 UTC (94 KB) [v2] Fri, 18 Jul 2025 05:07:38 UTC (94 KB) [v3] Mon, 28 Jul 2025 18:54:04 UTC (94 KB) [v4] Sun, 21 Jun 2026 09:03:48 UTC (126 KB) [v5] Mon, 24 Aug 2026 20:51:21 UTC (126 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.AI < prev | next > new | recent | 2025-07 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light#670359
• Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning#997438
• Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation#1155664
• Evolution imposes an inductive bias that alters and accelerates learning dynamics#261151
• Interpretable reinforcement learning with decision-tree pruning#440390