mlsanityData to 14 Oct 2026

Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control

arXiv 2512.01467 ↗First posted 1 Dec 2025cs.LG cs.AR cs.SCcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 60 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

34 of 60 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  6. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  7. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  8. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  9. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  10. 2020What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Studycited by 162
  11. 2022Deep Differentiable Logic Gate Networkscited by 67
  12. 2022The State of Sparse Training in Deep Reinforcement Learningcited by 61
22 more
  1. 2020Neurosymbolic Reinforcement Learning with Formally Verified Explorationcited by 49
  2. 2024Convolutional Differentiable Logic Gate Networkscited by 37
  3. 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
  4. 2022RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratchcited by 30
  5. 2024Differentiable Weightless Neural Networkscited by 28
  6. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  7. 2019QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learningcited by 19
  8. 2025Recurrent Deep Differentiable Logic Gate Networkscited by 12
  9. 2024Learning Interpretable Differentiable Logic Networkscited by 10
  10. 2025High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measurescited by 10
  11. 2025Differentiable Logic Cellular Automata: From Game of Life to Pattern Generationcited by 9
  12. 2024The Impact of Quantization and Pruning on Deep Reinforcement Learning Modelscited by 6
  13. 2025WARP-LUTs -- Walsh-Assisted Relaxation for Probabilistic Look Up Tablescited by 6
  14. 2025LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deploymentcited by 6
  15. 2025A Method for Optimizing Connections in Differentiable Logic Gate Networkscited by 5
  16. 2025Logic Gate Neural Networks are Good for Verificationcited by 4
  17. 2025Scalable Interconnect Learning in Boolean Networkscited by 4
  18. 2021Binarized P-Network: Deep Reinforcement Learning of Robot Control from Raw Images on FPGAcited by 3
  19. 2024Neural Network Compression for Reinforcement Learning Taskscited by 3
  20. 2024Towards Narrowing the Generalization Gap in Deep Boolean Networkscited by 3
  21. 2022Deep Binary Reinforcement Learning for Scalable Verificationcited by 2
  22. 2025Learning Quantized Continuous Controllers for Integer Hardwarecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flipscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Topological Feasibility Guarantees for Differentiable Predictive Control
  2. 2025Tiny Recursive Control: Iterative Reasoning for Efficient Optimal Control
  3. 2024Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control
  4. 2026Model-Free DRL Control for Power Inverters: From Policy Learning to Real-Time Implementation via Knowledge Distillation
  5. 2023Deep Inductive Logic Programming meets Reinforcement Learning
  6. 2026FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
  7. 2026Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks
  8. 2026Learning Nonlinear Systems In-Context: From Synthetic Data to Real-World Motor Control