mlsanityData to 7 Oct 2026

A Quadratic Actor Network for Model-Free Reinforcement Learning

arXiv 2103.06617 ↗First posted 11 Mar 2021cs.LG cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work we discuss the incorporation of quadratic neurons into policy networks in the context of model-free actor-critic reinforcement learning. Quadratic neurons admit an explicit quadratic function approximation in contrast to conventional approaches where the the non-linearity is induced by the activation functions. We perform empiric experiments on several MuJoCo continuous control tasks and find that when quadratic neurons are added to MLP policy networks those outperform the baseline MLP whilst admitting a smaller number of parameters. The top returned reward is in average increased by 5.8% while being about 21% more sample efficient. Moreover, it can maintain its advantage against added action and observation noise.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

28 of 41 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  7. 2015Continuous control with deep reinforcement learningcited by 3,279
  8. 2015Trust Region Policy Optimizationcited by 2,503
  9. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  10. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  11. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  12. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
16 more
  1. 2016OpenAI Gymcited by 1,684
  2. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  3. 2019The StarCraft Multi-Agent Challengecited by 589
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  5. 2018Maximum a Posteriori Policy Optimisationcited by 318
  6. 2015Taming the Noise in Reinforcement Learning via Soft Updatescited by 125
  7. 2018Composable Deep Reinforcement Learning for Robotic Manipulationcited by 70
  8. 2020A Distributional View on Multi-Objective Policy Optimizationcited by 51
  9. 2020Sim2Real Transfer for Reinforcement Learning without Dynamics Randomizationcited by 43
  10. 2018Universal Approximation with Quadratic Deep Networkscited by 29
  11. 2017A New Type of Neurons for Machine Learningcited by 16
  12. 2018Structured Control Nets for Deep Reinforcement Learningcited by 8
  13. 2020FORK: A Forward-Looking Actor For Model-Free Reinforcement Learningcited by 5
  14. 2020Efficient Neural Network Implementation with Quadratic Neuroncited by 2
  15. 2019Recurrent Control Nets for Deep Reinforcement Learningcited by 1
  16. 2020Deep Reinforcement Learning with Linear Quadratic Regulator Regionscited by 1

Built on by

Not cited yet.