paper-with-me

홈 › Papers

Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light

2025-07-15 · Mani Hamidi, Terrence W. Deacon

Three core tenets of reinforcement learning (RL)--concerning the definition of agency, the objective of learning, and the scope of the reward hypothesis--have been highlighted as key targets for conceptual revision, with major implications for theory and application. We propose a framework, inspired by open-ended evolutionary theory, to reconsider these three "dogmas." We revisit each assumption and address related concerns raised alongside them. To make our arguments relevant to RL as a model of biological learning, we first establish that evolutionary dynamics can plausibly operate within living brains over an individual's lifetime, and are not confined to cross-generational processes. We begin by revisiting the second dogma, drawing on evolutionary insights to enrich the "adaptation-rather-than-search" view of learning. We then address the third dogma regarding the limits of the reward hypothesis, using analogies from evolutionary fitness to illuminate the scalar reward vs. multi-objective debate. After discussing practical implications for exploration in RL, we turn to the first--and arguably most fundamental--issue: the absence of a formal account of agency. We argue that unlike the other two problems, the evolutionary paradigm alone cannot resolve the agency question, though it gestures in a productive direction. We advocate integrating ideas from origins-of-life theory, where the thermodynamics of sustenance and replication offer promising foundations for understanding agency and resource-constrained reinforcement learning in biological systems.

📄 PDF Abstract BibTeX arXiv:2507.11482

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Three Dogmas of Reinforcement Learning

2024-07-15 · David Abel, Mark K. Ho, Anna Harutyunyan

Modern reinforcement learning has been conditioned by at least three dogmas. The first is the environment spotlight, which refers to our tendency to focus on modeling environments rather than agents. The second is our tr…

reinforcement-learningReinforcement Learning

Liberating language research from dogmas of the 20th century

2015-09-09 · Ramon Ferrer-i-Cancho, Carlos Gómez-Rodríguez

A commentary on the article "Large-scale evidence of dependency length minimization in 37 languages" by Futrell, Mahowald & Gibson (PNAS 2015 112 (33) 10336-10341).

Phylogeny-informed fitness estimation

2023-06-06 · Alexander Lalejini, Matthew Andres Moreno, Jose Guadalupe Hernandez, Emily Dolson

Phylogenies (ancestry trees) depict the evolutionary history of an evolving population. In evolutionary computing, a phylogeny can reveal how an evolutionary algorithm steers a population through a search space, illumina…

DiagnosticDiversityEvolutionary Algorithms

Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning

2019-12-13 · Shuai Lü, Shuai Han, Wenbo Zhou, Junwei Zhang

Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters sett…

continuous-controlContinuous ControlEfficient ExplorationEvolutionary Algorithms+5

P^2O: Joint Policy and Prompt Optimization

2026-03-23 · Xinyu Lu, Kaiqi Zhang, Jinglin Yang, Boxi Cao 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail. This lack of variance eliminates crucia…

Reinforcement Learning