Pith. sign in

REVIEW 3 cited by

$\mathrm{SO}(2)$-Equivariant Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.04439 v1 pith:Z4CNLNQE submitted 2022-03-08 cs.RO

Dian Wang , Robin Walters , Robert Platt This is my paper · ORCID
classification cs.RO
keywords equivariantlearningalgorithmsfunctioninvariantmanipulationoptimalreinforcement
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Equivariant neural networks enforce symmetry within the structure of their convolutional layers, resulting in a substantial improvement in sample efficiency when learning an equivariant or invariant function. Such models are applicable to robotic manipulation learning which can often be formulated as a rotationally symmetric problem. This paper studies equivariant model architectures in the context of $Q$-learning and actor-critic reinforcement learning. We identify equivariant and invariant characteristics of the optimal $Q$-function and the optimal policy and propose equivariant DQN and SAC algorithms that leverage this structure. We present experiments that demonstrate that our equivariant versions of DQN and SAC can be significantly more sample efficient than competing algorithms on an important class of robotic manipulation problems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MatrixNet: Learning over symmetry groups using learned group representations

    cs.LG 2025-01 conditional novelty 7.0 of 10

    A neural network that learns matrix-valued group representations by design achieves near-perfect accuracy and length extrapolation on group prediction tasks, outperforming fixed-representation, MLP, LSTM, and Transfor...

  2. Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces

    cs.LG 2025-05 conditional novelty 6.0 of 10

    E-NES uses Lie-group point-cloud conditioning and equivariant neural fields to make grid-free eikonal travel-time prediction steerable under rotations and translations, with complete invariant features and competitive...

  3. Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control

    cs.RO 2025-09 conditional novelty 5.0 of 10

    LEGO couples agent-centric canonicalization with role-aware graph transformers in MAPPO to produce E(2)-equivariant, zero-shot scalable swarm control policies.

Pith tools