微分可能な無重みコントローラ:連続制御のための論理回路学習
Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control
勾配法で学習でき、FPGA上で超低遅延・低消費電力に動作する論理回路ベースの制御ポリシーを提案し、MuJoCoベンチマークで深層強化学習に匹敵する性能を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Fabian Kresse, Christoph H. Lampert
分類: cs.LG, cs.AR, cs.SC
原文アブストラクト
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.
