الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve to improve how agents learn. However, realizing this prospect faces two obstacles. Joint search over coupled algorithmic components is difficult to scale: simultaneous changes can disrupt learning, while isolated changes overlook their dependencies. Evaluating candidate algorithms also requires costly training, with fitness remaining uncertain across random seeds. We introduce RLDiscover, a framework for the self-evolution of model-free deep RL algorithms. Progressive Co-Evolution advances from targeted component edits to joint evolution, while Progressive Probabilistic Evaluation balances search breadth and evaluation fidelity through staged training and repeated evaluation. Experiments across SAC, PPO, and DQN on four benchmark suites show substantial improvements in mean return, with per-family median gains of 32%-84% and a peak return ratio of approximately 363x over a near-zero baseline. These gains include transitions from failed learning to successful task completion, and improvements persist when evolution starts from stronger open-source implementations. On measured SAC locomotion runs, evaluation uses approximately one-fifteenth the estimated compute required to fully evaluate the same candidate pool. Remarkably, independent searches repeatedly discover interpretable combinations of adaptive robust losses, progress-dependent value targets, and running statistics, with selected programs transferring to unseen tasks. These findings point toward a broader role for self-evolution in AI: discovering interpretable algorithms that improve how agents learn.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Li, H., Ge, Z., Yuan, X., Lo, Y., Zhou, S., Ying, J., Li, H., Liu, Q., Liu, Y., Liu, J., Chen, G., Chen, M., Wang, R., Li, A., Wu, J., Yin, D., & Shen, D. (2026). RLDISCOVER: التطور المشترك لخوارزميات التعلم المعزز المدفوع بالنماذج اللغوية الكبيرة. https://omanscience.com/ar/articles/rldiscover-llm-driven-co-evolution-of-reinforcement-learning-algorithms
MLA 9
Li, Haoran, et al. "RLDISCOVER: التطور المشترك لخوارزميات التعلم المعزز المدفوع بالنماذج اللغوية الكبيرة." https://omanscience.com/ar/articles/rldiscover-llm-driven-co-evolution-of-reinforcement-learning-algorithms.
شيكاغو (المؤلف–التاريخ)
Li, Haoran, Zengle Ge, Xiaomin Yuan, Yui Lo, Songlin Zhou, Jiahua Ying, Haoxin Li, Qianhui Liu, Yuanhang Liu, Jiaqun Liu, Guokai Chen, Mingju Chen, Ruinan Wang, Annan Li, Jianmin Wu, Dawei Yin, and Dou Shen. 2026. "RLDISCOVER: التطور المشترك لخوارزميات التعلم المعزز المدفوع بالنماذج اللغوية الكبيرة." https://omanscience.com/ar/articles/rldiscover-llm-driven-co-evolution-of-reinforcement-learning-algorithms.
هارفارد
Li, H., Ge, Z., Yuan, X., Lo, Y., Zhou, S., Ying, J., Li, H., Liu, Q., Liu, Y., Liu, J., Chen, G., Chen, M., Wang, R., Li, A., Wu, J., Yin, D. and Shen, D. (2026) 'RLDISCOVER: التطور المشترك لخوارزميات التعلم المعزز المدفوع بالنماذج اللغوية الكبيرة', Available at: https://omanscience.com/ar/articles/rldiscover-llm-driven-co-evolution-of-reinforcement-learning-algorithms.
فانكوفر
Li H, Ge Z, Yuan X, Lo Y, Zhou S, Ying J, et al. RLDISCOVER: التطور المشترك لخوارزميات التعلم المعزز المدفوع بالنماذج اللغوية الكبيرة. https://omanscience.com/ar/articles/rldiscover-llm-driven-co-evolution-of-reinforcement-learning-algorithms
IEEE
H. Li, Z. Ge, X. Yuan, Y. Lo, S. Zhou, J. Ying, H. Li, Q. Liu, Y. Liu, J. Liu, G. Chen, M. Chen, R. Wang, A. Li, J. Wu, D. Yin, and D. Shen, "RLDISCOVER: التطور المشترك لخوارزميات التعلم المعزز المدفوع بالنماذج اللغوية الكبيرة," https://omanscience.com/ar/articles/rldiscover-llm-driven-co-evolution-of-reinforcement-learning-algorithms.