mlsanityData to 14 Oct 2026

Integrating Symmetry into Differentiable Planning with Steerable Convolutions

arXiv 2206.03674 ↗First posted 8 Jun 2022cs.LG cs.AI cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks, we treat the path planning problem as textitsignals over grids. We show that value iteration in this case is a linear equivariant operator, which is a (steerable) convolution. This extends Value Iteration Networks (VINs) on using convolutional networks for path planning with additional rotation and reflection symmetry. Our implementation is based on VINs and uses steerable convolution networks to incorporate symmetry. The experiments are performed on four tasks: 2D navigation, visual navigation, and 2 degrees of freedom (2DOFs) configuration space and workspace manipulation. Our symmetric planning algorithms improve training efficiency and generalization by large margins compared to non-equivariant counterparts, VIN and GPPN.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 34 of its 85 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

34 of 85 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  4. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  5. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  6. 2016Group Equivariant Convolutional Networkscited by 1,165
  7. 2018Spherical CNNscited by 456
  8. 2019General E(2)-Equivariant Steerable CNNscited by 446
  9. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  10. 2016Steerable CNNscited by 305
  11. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 300
  12. 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 228
22 more
  1. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  2. 2018Differentiable MPC for End-to-end Planning and Controlcited by 189
  3. 2016Value Iteration Networkscited by 160
  4. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 142
  5. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 140
  6. 2017Value Prediction Networkcited by 117
  7. 2020The Value Equivalence Principle for Model-Based Reinforcement Learningcited by 94
  8. 2019Exploring Model-based Planning with Policy Networkscited by 90
  9. 2018Temporal Difference Models: Model-Free Deep RL for Model-Based Controlcited by 89
  10. 2019An investigation of model-free planningcited by 66
  11. 2020Model-Augmented Actor-Critic: Backpropagating through Pathscited by 63
  12. 2022Learning Symmetric Embeddings for Equivariant World Modelscited by 54
  13. 2017QMDP-Net: Deep Learning for Planning under Partial Observabilitycited by 51
  14. 2021Proper Value Equivalencecited by 33
  15. 2018Gated Path Planning Networkscited by 31
  16. 2018Universal Planning Networkscited by 30
  17. 2019The Differentiable Cross-Entropy Methodcited by 27
  18. 2021Differentiable Spatial Planning using Transformerscited by 25
  19. 2020Group Equivariant Deep Reinforcement Learningcited by 24
  20. 2022Toward Compositional Generalization in Object-Oriented World Modelingcited by 22
  21. 2021Neural Algorithmic Reasoners are Implicit Plannerscited by 21
  22. 2017Generalized Value Iteration Networks: Life Beyond Latticescited by 16

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 2.

6 papers.

  1. 2023A General Theory of Correct, Incorrect, and Extrinsic Equivariancecited by 19
  2. 2022Scaling up and Stabilizing Differentiable Planning with Implicit Differentiationcited by 6
  3. 2023E(2)-Equivariant Graph Planning for Navigationcited by 6
  4. 2024Equivariant Action Sampling for Reinforcement Learning and Planningcited by 4
  5. 2024Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Mapscited by 2
  6. 2023Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?cited by 1