外观
论文HF Daily Papers · arXiv 2610.346383 天前
果蝇全脑记录验证DIAYN层级内在动机算法复现自主探索
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila（HF Daily Papers · arXiv 2610.34638）
核心内容
研究团队结合果蝇全脑神经记录与神经机械数字孪生系统，揭示了生物体在无外部感官线索下提前10秒以上产生自发探索决策的神经机制。通过在虚拟系留球实验平台上测试20种涵盖好奇心、熵及能力方法的内在动机算法，证实基于层级能力的DIAYN算法在联合行为统计与神经前瞻性编码性能上最接近真实果蝇，成功量化复现了生物自主性。
DIAYN算法采用离散运动基元库构建层级策略，通过最大化行为熵与诱导感官观测的可分离性进行无监督训练。其学习到的策略不仅捕捉了果蝇个体探索策略的变异性以实现种群级状态空间覆盖，其潜在活动还精确复现了生物果蝇运动学编码的半球间“和-差规则”。该框架确立了层级内在动机代理作为逆向工程动物自主性的有效计算范式。
关键看点
- 决策预测时延：全脑记录显示果蝇自发探索决策的神经表征先于动作10秒以上，DIAYN代理在同时间尺度上复现了该前瞻性编码。
- DIAYN算法机制：采用离散策略库最大化行为熵与感官观测可分离性，在无外部奖励训练中实现最优的行为与神经联合匹配度。
- 神经编码对齐：算法潜在活动精确捕获生物果蝇运动学编码的半球间“和-差规则”，验证了人工代理内部表征的生物学合理性。
- 运动基元架构：基于离散低层运动基元库的层级策略符合行为音节理论，有效解释了个体探索差异对种群状态空间覆盖的贡献。
工程与产业观察
该研究为具身智能“内生驱动力”提供了严格的生物学对齐基准。DIAYN在无奖励条件下复现果蝇长时序决策与神经编码，证明基于离散技能原语的层级内在动机是解决稀疏奖励探索难题的有效路径。这提示机器人自主学习应重视行为多样性与神经表征一致性，而非仅优化任务指标，对构建类生物自主性的通用具身模型具有重要参考价值。
英文摘要 (Abstract)
Animals have a remarkable capacity for autonomy---driven by intrinsic motivation---without external sensory cues or extrinsic objectives, yet the computational mechanisms behind this ability largely remain a mystery. We combine whole-brain recordings in the fruit fly (Drosophila melanogaster), which reveal neural representations of spontaneous exploratory decisions more than 10 seconds in advance, with a neuromechanical digital twin to test whether optimizing intrinsic goals yields realistically embodied artificial agents that quantitatively match fly behavior and internal representations of future volitional action during exploration. Our hierarchical policy selects from a discrete library of low-level motor primitives, consistent with ethological theories of behavioral syllables. We train agents without external reward using 20 intrinsic motivation algorithms spanning curiosity, entropy, and competency methods. The agents are evaluated in a virtual tethered-ball assay modeled on the fly experiment, comparing spontaneous locomotor statistics and internal representations and decoding future turn direction from kinematics and neural activity on the same timescales observed in flies. DIAYN, a hierarchical competency algorithm learning discrete policies that maximize behavioral entropy and the separability of induced sensory observations, achieves the strongest joint behavioral and neural prospective coding performance relative to flies. Its learned policies closely capture individual variability in fly exploration strategies, suggesting that this diversity serves to maximize state-space coverage at the population level. DIAYN's latent activity also closely captures the sum-difference rule for interhemispheric encoding of kinematics in biological flies. These results establish hierarchical, intrinsically motivated agents as a powerful framework for reverse-engineering animal autonomy.
Hugging Face Daily Papers 热度：2 upvotes 作者：Declan Kutscher, Reece Keller, Alyn Kirsch, Felix Pei, Aran Nayebi
来源
本页事实对应的公开页面，以原文为准。