进化强化学习中神经策略与编程策略的生存动态
Survival Dynamics of Neural and Programmatic Policies in Evolutionary Reinforcement Learning
AI总结：
研究进化强化学习中神经策略与编程策略的生存动态，通过开源重新实现经典测试平台并进行严格生存分析，发现编程策略在生存性能上超越神经策略，如PERL比NERL平均多存活201.69步。
摘要：
在进化强化学习任务中，智能体策略常编码为小型人工神经网络，缺乏明确模块化结构，限制行为解释。本文研究作为软可微决策列表实现的编程策略能否匹配神经策略性能。提供经典1992年人工生命进化强化学习测试平台首个完全指定的开源重新实现，通过严格生存分析发现编程策略与神经策略生存概率有显著差异，编程策略平均比神经策略多存活201.69步，仅使用学习的软可微决策列表智能体比同时使用学习和评估的神经智能体平均多存活73.67步。
英文摘要：
In evolutionary reinforcement learning tasks (ERL), agent policies are often encoded as small artificial neural networks (NERL). Such representations lack explicit modular structure, limiting behavioral interpretation. We investigate whether programmatic policies (PERL), implemented as soft, differentiable decision lists (SDDL), can match the performance of NERL. To support reproducible evaluation, we provide the first fully specified and open-source reimplementation of the classic 1992 Artificial Life (ALife) ERL testbed. We conduct a rigorous survival analysis across 4000 independent trials utilizing Kaplan-Meier curves and Restricted Mean Survival Time (RMST) metrics absent in the original study. We find a statistically significant difference in survival probability between PERL and NERL. PERL agents survive on average 201.69 steps longer than NERL agents. Moreover, SDDL agents using learning alone (no evolution) survive on average 73.67 steps longer than neural agents using both learning and evaluation. These results demonstrate that programmatic policies can exceed the survival performance of neural policies in ALife.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
