arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.08554q-bio.NCcs.AIcs.LGcs.NE
收藏

神经元回路策略

Neuronal Circuit Policies

TU Wien(维也纳工业大学)

Mathias Lechner, Ramin M. Hasani, Radu Grosu

摘要:

我们提出了一种有效的方法来创建可解释的控制代理,通过重新利用生物神经电路模型的功能,来管理模拟和现实世界的强化学习(RL)测试床。我们模拟了线虫C. elegans,负责蠕虫对外部机械触摸刺激的反射性反应的电路,并学习其突触和神经元参数作为控制基本RL任务的策略。我们还自主地将一个真正的漫游机器人停放在预定义的轨迹上,通过部署在模拟环境中学习的神经元电路策略。对于TW神经电路的重构目的,我们采用了基于搜索的RL算法。我们表明,我们的神经元政策表现得与深度神经网络政策一样好,其优势是在细胞水平上实现可解释的动态。

英文摘要:

We propose an effective way to create interpretable control agents, by re-purposing the function of a biological neural circuit model, to govern simulated and real world reinforcement learning (RL) test-beds. We model the tap-withdrawal (TW) neural circuit of the nematode, C. elegans, a circuit responsible for the worm's reflexive response to external mechanical touch stimulations, and learn its synaptic and neuronal parameters as a policy for controlling basic RL tasks. We also autonomously park a real rover robot on a pre-defined trajectory, by deploying such neuronal circuit policies learned in a simulated environment. For reconfiguration of the purpose of the TW neural circuit, we adopt a search-based RL algorithm. We show that our neuronal policies perform as good as deep neural network policies with the advantage of realizing interpretable dynamics at the cell level.

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。

↑