mlsanityData to 7 Oct 2026

Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigation

arXiv 2403.14583 ↗First posted 21 Mar 2024cs.RO cs.LG cs.MAcited by 4

Not on the map. Why?

Abstract (arXiv)

This work views the multi-agent system and its surrounding environment as a co-evolving system, where the behavior of one affects the other. The goal is to take both agent actions and environment configurations as decision variables, and optimize these two components in a coordinated manner to improve some measure of interest. Towards this end, we consider the problem of decentralized multi-agent navigation in a cluttered environment, where we assume that the layout of the environment is reconfigurable. By introducing two sub-objectives -- multi-agent navigation and environment optimization -- we propose an agent-environment co-optimization problem and develop a coordinated algorithm that alternates between these sub-objectives to search for an optimal synthesis of agent actions and environment configurations; ultimately, improving the navigation performance. Due to the challenge of explicitly modeling the relation between the agents, the environment and their performance therein, we leverage policy gradient to formulate a model-free learning mechanism within the coordinated framework. A formal convergence analysis shows that our coordinated algorithm tracks the local minimum solution of an associated time-varying non-convex optimization problem. Experiments corroborate theoretical findings and show the benefits of co-optimization. Interestingly, the results also indicate that optimized environments can offer structural guidance to de-conflict agents in motion.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 88 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

28 of 88 references.

References · 28

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Graph Attention Networkscited by 8,854
  3. 2021Convex optimizationcited by 2,479
  4. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 633
  5. 2018On Evaluation of Embodied Navigation Agentscited by 526
  6. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 304
  7. 2022Navigating to Objects in the Real Worldcited by 104
  8. 2018Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learningcited by 101
  9. 2019Graph Neural Networks for Decentralized Multi-Robot Path Planningcited by 84
  10. 2019Learning Decentralized Controllers for Robot Swarms with Graph Neural Networkscited by 62
  11. 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 51
  12. 2017Scalable Co-Optimization of Morphology and Control in Embodied Machinescited by 38
16 more
  1. 2016Real-time optimal control via Deep Neural Networks: study on landing problemscited by 27
  2. 2014Prioritized Planning Algorithms for Trajectory Coordination of Multiple Mobile Robotscited by 19
  3. 2021Wide and Deep Graph Neural Network with Distributed Online Learningcited by 14
  4. 2021Adversarial Environment Generation for Learning to Navigate the Webcited by 13
  5. 2023Online Control Barrier Functions for Decentralized Multi-Agent Navigationcited by 10
  6. 2019Multi-Robot Path Deconfliction through Prioritization by Path Prospectscited by 8
  7. 2020Designing Environments Conducive to Interpretable Robot Behaviorcited by 8
  8. 2022Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigationcited by 8
  9. 2022Environment Optimization for Multi-Agent Navigationcited by 6
  10. 2023Constrained Environment Optimization for Prioritized Multi-Agent Navigationcited by 6
  11. 2015SDP-based Joint Sensor and Controller Design for Information-regularized Optimal LQG Controlcited by 4
  12. 2017Sensing-Constrained LQG Controlcited by 4
  13. 2020Decentralized Motion Planning for Multi-Robot Navigation using Deep Reinforcement Learningcited by 4
  14. 2022Standby-Based Deadlock Avoidance Method for Multi-Agent Pickup and Delivery Taskscited by 4
  15. 2019Escaping spurious local minimum trajectories in online time-varying nonconvex optimizationcited by 3
  16. 2019Optimal WDM Power Allocation via Deep Learning for Radio on Free Space Optics Systemscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordinationcited by 0
  2. 2026Stochastic Sequential Decision Making over Expanding Networks with Graph Filteringcited by 0
  3. 2026GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimizationcited by 0
  4. 2026Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotationscited by 0