paper-with-me

홈 › Papers

Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models

2026-03-30 · Alkis Sygkounas, Amy Loutfi, Andreas Persson arxiv

Reinforcement learning algorithms are defined by their learning update rules, which are typically hand-designed and fixed. We present an evolutionary framework for discovering reinforcement learning algorithms by searching directly over executable update rules that implement complete training procedures. The approach builds on REvolve, an evolutionary system that uses large language models as generative variation operators, and extends it from reward-function discovery to algorithm discovery. To promote the emergence of nonstandard learning rules, the search excludes canonical mechanisms such as actor--critic structures, temporal-difference losses, and value bootstrapping. Because reinforcement learning algorithms are highly sensitive to internal scalar parameters, we introduce a post-evolution refinement stage in which a large language model proposes feasible hyperparameter ranges for each evolved update rule. Evaluated end-to-end by full training runs on multiple Gymnasium benchmarks, the discovered algorithms achieve competitive performance relative to established baselines, including SAC, PPO, DQN, and A2C.

📄 PDF Abstract BibTeX arXiv:2603.28416

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning

2025-04-07 · Anja Surina, Amin Mansouri, Lars Quaedvlieg, Amal Seddas 외

Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years. Recent advancements in evolutiona…

Combinatorial Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning

2026-06-18 · Alan Nadelsticher Ruvalcaba arxiv

The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression of motivational priorities largely unexplored. In this wo…

Reinforcement Learning

Learning Interestingness in Automated Mathematical Theory Formation

2025-11-05 · George Tsoukalas, Rahul Saha, Amitayush Thakur, Sabrina Reguyal 외 arxiv

We take two key steps in automating the open-ended discovery of new mathematical theories, a grand challenge in artificial intelligence. First, we introduce $\emph{FERMAT}$, a reinforcement learning (RL) environment that…

Reinforcement Learning

Data-Driven Discovery of Interpretable Kalman Filter Variants through Large Language Models and Genetic Programming

2025-08-13 · Vasileios Saketos, Sebastian Kaltenbach, Sergey Litvinov, Petros Koumoutsakos arxiv

Algorithmic discovery has traditionally relied on human ingenuity and extensive experimentation. Here we investigate whether a prominent scientific computing algorithm, the Kalman Filter, can be discovered through an aut…

Effective Harness Engineering for Algorithm Discovery with Coding Agents

2026-05-13 · Yoichi Ishibashi, Taro Yano, Masafumi Oyamada arxiv

AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm discovery. However, discovery success is shaped not only by model capab…