Integrating Symmetry into Differentiable Planning with Steerable Convolutions. (arXiv:2206.03674v2 [cs.LG] UPDATED)

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 \textit{signals} 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 …

arxiv planning symmetry