mlsanityData to 7 Oct 2026

Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning

arXiv 1702.03118 ↗First posted 10 Feb 2017cs.LGcited by 935

Not on the map. Why?

Cited by 117 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). The activation of the SiLU is computed by the sigmoid function multiplied by its input. Second, we suggest that the more traditional approach of using on-policy learning with eligibility traces, instead of experience replay, and softmax action selection with simple annealing can be competitive with DQN, without the need for a separate target network. We validate our proposed approach by, first, achieving new state-of-the-art results in both stochastic SZ-Tetris and Tetris with a small 10×10 board, using TD(λ) learning and shallow dSiLU network agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa(λ) agent with SiLU and dSiLU hidden units.

Key facts. Cited by 935 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 60; 2022: 73; 2023: 129; 2024: 249; 2025: 239; 2026: 185.

935 papers.

Sort:

By area:

  1. 2024VMamba: Visual State Space Modelcited by 955
  2. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 821
  3. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  4. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  5. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  6. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  7. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  8. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 437
  9. 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Lengthcited by 373
  10. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  11. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 342
  12. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
38 more
  1. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 286
  2. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
  3. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  4. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  5. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 258
  6. 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 237
  7. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  8. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 222
  9. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  10. 2021Autoregressive Diffusion Modelscited by 208
  11. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 201
  12. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  13. 2022Transformer Quality in Linear Timecited by 189
  14. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 184
  15. 2022MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Modelcited by 180
  16. 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 179
  17. 2022Mega: Moving Average Equipped Gated Attentioncited by 178
  18. 2024Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modelingcited by 167
  19. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  20. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 156
  21. 2021Activation Functions in Deep Learning: A Comprehensive Survey and Benchmarkcited by 153
  22. 2023LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-Oncited by 151
  23. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  24. 2022Decoupling Features in Hierarchical Propagation for Video Object Segmentationcited by 146
  25. 2023TryOnDiffusion: A Tale of Two UNetscited by 141
  26. 2023Transformer-based World Models Are Happy With 100k Interactionscited by 137
  27. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  28. 2023Focused Transformer: Contrastive Training for Context Scalingcited by 133
  29. 2022KronA: Parameter Efficient Tuning with Kronecker Adaptercited by 130
  30. 2022DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problemscited by 127
  31. 2024ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Modelcited by 118
  32. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  33. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 113
  34. 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNscited by 113
  35. 2024Is Mamba Effective for Time Series Forecasting?cited by 110
  36. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
  37. 2023DiffiT: Diffusion Vision Transformers for Image Generationcited by 104
  38. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103

50 most cited of 935 All 935 (JSON)