神经网络自进化：无需外部优化器，自主变异与适应。
Hypernetworks That Evolve Themselves
- 用图结构超网络实现自我变异与遗传机制。
- 在多个基准上快速适应环境变化，自动生成稳定步态。
- 适合研究自进化智能体与开放域学习的学者。
如何让神经网络在不依赖外部优化器的情况下自我演化？我们提出自指图超网络（Self-Referential GHNs），将变异与遗传机制内嵌于网络自身。通过融合超网络、随机参数生成与图结构表示，该系统可自主变异、评估，并将突变率作为可选性状进行动态调整。在包含环境切换的新强化学习基准（CartPoleSwitch、LunarLander-Switch）中，其展现出快速可靠的适应能力与涌现的种群动态。在Ant-v5行走任务中，系统演化出协调步态，通过自主降低种群变异度，集中搜索优质解，表现出良好的微调潜力。研究结果表明，可演化性本身可从神经自我参照中涌现。自指图超网络朝着更接近生物进化的合成系统迈出一步，为自主、开放式的学习智能体提供了新工具。
原文摘要 · Abstract (English)
How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and inheritance is embedded within the network. By uniting hypernetworks, stochastic parameter generation, and graph-based representations, Self-Referential GHNs mutate and evaluate themselves while adapting mutation rates as selectable traits. Through new reinforcement learning benchmarks with environmental shifts (CartPoleSwitch, LunarLander-Switch), Self-Referential GHNs show swift, reliable adaptation and emergent population dynamics. In the locomotion benchmark Ant-v5, they evolve coherent gaits, showing promising fine-tuning capabilities by autonomously decreasing variation in the population to concentrate around promising solutions. Our findings support the idea that evolvability itself can emerge from neural self-reference. Self-Referential GHNs reflect a step toward synthetic systems that more closely mirror biological evolution, offering tools for autonomous, open-ended learning agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。