mlsanityData to 7 Oct 2026

Effects of Spectral Normalization in Multi-agent Reinforcement Learning

arXiv 2212.05331 ↗First posted 10 Dec 2022cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents 2) This, combined with the reward sparseness and environment noise, leads to large sample requirements for accurate learning. We show that regularising the critic with spectral normalization (SN) enables it to learn more robustly, even in multi-agent on-policy sparse reward scenarios. Our experiments show that the regularised critic is quickly able to learn from the sparse rewarding experience in the complex SMAC and RWARE domains. These findings highlight the importance of regularisation in the critic for stable learning.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 10 Dec 2022.

Builds on

26 of 38 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  6. 2017Hindsight Experience Replaycited by 1,096
  7. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  8. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  9. 2020MOPO: Model-based Offline Policy Optimizationcited by 630
  10. 2019The StarCraft Multi-Agent Challengecited by 589
  11. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  12. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
14 more
  1. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  2. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  3. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
  4. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 207
  5. 2019MAVEN: Multi-Agent Variational Explorationcited by 181
  6. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  7. 2015Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networkscited by 121
  8. 2017The Numerics of GANscited by 104
  9. 2021Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspectivecited by 64
  10. 2019Competitive Gradient Descentcited by 32
  11. 2020UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learningcited by 32
  12. 2021Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learningcited by 25
  13. 2022Generalization in Cooperative Multi-Agent Systemscited by 18
  14. 2017Symmetry Learning for Function Approximation in Reinforcement Learningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 0; 2025: 1; 2026: 1.

6 papers.

  1. 2023Normalization Enhances Generalization in Visual Reinforcement Learningcited by 13
  2. 2023Alpha Elimination: Using Deep Reinforcement Learning to Reduce Fill-In during Sparse Matrix Decompositioncited by 4
  3. 2023Angle based dynamic learning rate for gradient descentcited by 2
  4. 2026SignMuon: Communication-Efficient Distributed Muon Optimizationcited by 2
  5. 2023Nonnegative Low-Rank Tensor Completion via Dual Formulation with Applications to Image and Video Completioncited by 1
  6. 2025Unifying Agent Interaction and World Information for Multi-agent Coordinationcited by 1