用可微符号架构实现低延迟、低功耗的连续控制，性能媲美深度网络
Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control
- 提出可微分无权重控制器，将逻辑电路与梯度训练结合
- 在5个MuJoCo任务中表现接近全精度神经网络，单次动作能耗达纳焦级
- 结构稀疏可解释，适合对可靠性与能效要求高的嵌入式系统
在真实环境中控制自主系统通常需要低延迟、低功耗的策略。然而，高精度深度神经网络作为控制器难以满足这一需求。本文提出可微分无权重控制器（DWCs），一种符号可微架构，能够学习灵活、非线性且高度高效的控制策略。DWCs可通过基于梯度的方法端到端训练，同时直接编译为可在FPGA上运行的电路，单周期或少数周期内完成推理，每次动作能耗低至纳焦级别。在五个MuJoCo基准测试中，包括高维Humanoid任务，DWCs达到与标准深度策略（全精度或量化神经网络）相当的回报。此外，DWCs展现出结构稀疏且可解释的连接模式，可直接分析哪些输入值影响控制决策。
原文摘要 · Abstract (English)
Controlling autonomous systems under real-world conditions often requires policies that can be evaluated with low latency and minimal energy consumption. Unfortunately, these conditions are at odds with the use of high-precision deep neural networks as controllers. In this work, we introduce Differentiable Weightless Controllers (DWCs), a symbolic-differentiable architecture that learns flexible, non-linear, yet highly efficient control policies. DWCs can be trained end-to-end via gradient-based techniques, yet compile directly into FPGA-compatible circuits with few- or even single-clock-cycle latency and nanojoule-level energy cost per action. Across five MuJoCo benchmarks, including high-dimensional Humanoid, DWCs achieve returns competitive with standard deep policies (full-precision or quantized neural networks). Furthermore, DWCs exhibit structurally sparse and interpretable connectivity patterns, enabling direct inspection of which input values influence control decisions.
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。