mlsanityData to 14 Oct 2026

Subequivariant Reinforcement Learning Framework for Coordinated Motion Control

arXiv 2403.15100 ↗First posted 22 Mar 2024cs.RO cs.AIcited by 2

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Effective coordination is crucial for motion control with reinforcement learning, especially as the complexity of agents and their motions increases. However, many existing methods struggle to account for the intricate dependencies between joints. We introduce CoordiGraph, a novel architecture that leverages subequivariant principles from physics to enhance coordination of motion control with reinforcement learning. This method embeds the principles of equivariance as inherent patterns in the learning process under gravity influence, which aids in modeling the nuanced relationships between joints vital for motion control. Through extensive experimentation with sophisticated agents in diverse environments, we highlight the merits of our approach. Compared to current leading methods, CoordiGraph notably enhances generalization and sample efficiency.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 29 of its 52 references that are in the map. First posted on arXiv 22 Mar 2024.

Builds on

29 of 52 references.

References · 29

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  2. 2021E(n) Equivariant Graph Neural Networkscited by 965
  3. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  5. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  6. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  7. 2018Graph Convolutional Reinforcement Learningcited by 152
  8. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 116
  9. 2020Explainability in Deep Reinforcement Learningcited by 97
  10. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  11. 2022Equivariant Graph Mechanics Networks with Constraintscited by 68
  12. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
17 more
  1. 2021Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learningcited by 52
  2. 2022Reinforced Genetic Algorithm for Structure-based Drug Designcited by 46
  3. 2021Deep Reinforcement Learning in Computer Vision: A Comprehensive Surveycited by 43
  4. 2022Learning Physical Dynamics with Subequivariant Graph Neural Networkscited by 39
  5. 2022Low Dimensional Invariant Embeddings for Universal Geometric Learningcited by 38
  6. 2020JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognitioncited by 33
  7. 2021Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systemscited by 28
  8. 2021IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learningcited by 26
  9. 2022Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognitioncited by 24
  10. 2019Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spacescited by 16
  11. 2020Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environmentscited by 13
  12. 2021Comparing Popular Simulation Environments in the Scope of Robotics and Reinforcement Learningcited by 12
  13. 2022Finding Diverse and Predictable Subgraphs for Graph Domain Generalizationcited by 9
  14. 2019Hybrid Zero Dynamics Inspired Feedback Control Policy Design for 3D Bipedal Locomotion using Reinforcement Learningcited by 8
  15. 2021Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezingcited by 7
  16. 2021Graph Attention Network-based Multi-agent Reinforcement Learning for Slicing Resource Management in Dense Cellular Networkcited by 7
  17. 2019Performing Deep Recurrent Double Q-Learning for Atari Gamescited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfindingcited by 21
  2. 2024Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Modelscited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2024Leveraging Symmetry in RL-based Legged Locomotion Control
  2. 2026Sample Complexity of Equivariant Reinforcement Learning
  3. 2025Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation
  4. 2026Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
  5. 2024Equivariant Action Sampling for Reinforcement Learning and Planning
  6. 2025Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy
  7. 2026Foundations of Reinforcement Learning and Control:Connections and New Perspectives
  8. 2025Equivariant Goal Conditioned Contrastive Reinforcement Learning