mlsanityData to 7 Oct 2026

Group Equivariant Deep Reinforcement Learning

arXiv 2007.03437 ↗First posted 1 Jul 2020cs.LG cs.AI stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn action-value functions and policies in various environments. However, to date, there has been little work on the learning of symmetry-transformation equivariant representations of the input environment state. In this paper, we propose the use of Equivariant CNNs to train RL agents and study their inductive bias for transformation equivariant Q-value approximation. We demonstrate that equivariant architectures can dramatically enhance the performance and sample efficiency of RL agents in a highly symmetric environment while requiring fewer parameters. Additionally, we show that they are robust to changes in the environment caused by affine transformations.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 7; 2024: 4; 2025: 3; 2026: 1.

22 papers.

Sort:

By area:

  1. 2022Equivariance with Learned Canonicalization Functionscited by 106
  2. 2023Equivariant Adaptation of Large Pretrained Modelscited by 40
  3. 2022The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetrycited by 32
  4. 2021Self-Interpretable Model with TransformationEquivariant Interpretationcited by 21
  5. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  6. 2024Equivariant Reinforcement Learning under Partial Observabilitycited by 17
  7. 2022Equivariant Networks for Zero-Shot Coordinationcited by 16
  8. 2023On Robot Grasp Learning Using Equivariant Modelscited by 12
  9. 2023Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networkscited by 9
  10. 2024Approximate Equivariance in Reinforcement Learningcited by 9
  11. 2024Improved Canonicalization for Model Agnostic Equivariancecited by 7
  12. 2022Integrating Symmetry into Differentiable Planning with Steerable Convolutionscited by 6
10 more
  1. 2023E(2)-Equivariant Graph Planning for Navigationcited by 6
  2. 2024Equivariant Offline Reinforcement Learningcited by 5
  3. 2023Addressing imperfect symmetry: A novel symmetry-learning actor-critic extensioncited by 4
  4. 20253D Equivariant Visuomotor Policy Learning via Spherical Projectioncited by 4
  5. 2022ReF -- Rotation Equivariant Features for Local Feature Matchingcited by 2
  6. 2023Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?cited by 1
  7. 2025Symmetries-enhanced Multi-Agent Reinforcement Learningcited by 1
  8. 2025Learning Abstract World Models with a Group-Structured Latent Spacecited by 1
  9. 2023Learning Geometric Representations of Objects via Interactioncited by 0
  10. 2026SymVD: Symmetric Vision Language Action Distillation for Robot Manipulationcited by 0