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

• URL: http://arxiv.org/abs/2403.14583v2
• Date: Wed, 02 Jul 2025 12:37:15 GMT
• Title: Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigation
• Abstract summary: This work views the multi-agent system and its surrounding environment as a co-evolving system, where the behavior of one affects the other.<n>By introducing two sub-objectives -- multi-agent navigation and environment optimization -- we propose an agent co-optimization problem.
• Score: 14.533605727697775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ASPaeroFlow: Decomposition Heuristics for Joint Air Traffic Flow & Capacity Management [60.85136195443409]
  We propose ASPaeroFlow: a for the joint Air Traffic Flow and Capacity Management (ATFCM)<n>It combines instance-space decompositions with a local exact approach using Answer Set Programming.<n>We benchmark ASPaeroFlow from small to industry-sized instances and compare it with exact and alternative approaches.
  arXiv  Detail & Related papers  (2026-08-10T08:57:18Z)
• Differentiable Environment-Trajectory Co-Optimization for Safe Multi-Agent Navigation [27.7147161884966]
  The environment plays a critical role in multi-agent navigation by imposing spatial constraints, rules, and limitations that agents must navigate around.<n>This work considers environment configurations as decision variables, alongside agent actions, to jointly achieve safe navigation.
  arXiv  Detail & Related papers  (2026-04-08T11:43:38Z)
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• Grounded Test-Time Adaptation for LLM Agents [75.62784644919803]
  Large language model (LLM)-based agents struggle to generalize to novel and complex environments.<n>We propose two strategies for adapting LLM agents by leveraging environment-specific information available during deployment.
  arXiv  Detail & Related papers  (2025-11-06T22:24:35Z)
• Scaling Multi-Agent Environment Co-Design with Diffusion Models [15.05916455401006]
  Agent-environment co-design aims to jointly optimise agent policies and environment configurations in search of improved system performance.<n>Current co-design methods struggle to scale, collapse under high-dimensional environment design spaces and suffer from sample inefficiency.<n>We develop a scalable and sample-efficient co-design framework pushing co-design towards practically relevant settings.<n>Our method consistently exceeds the state-of-the-art, achieving 39% higher rewards in the warehouse setting with 66% fewer simulation samples.
  arXiv  Detail & Related papers  (2025-11-05T01:09:40Z)
• Joint Optimization of Cooperation Efficiency and Communication Covertness for Target Detection with AUVs [105.81167650318054]
  This paper investigates underwater cooperative target detection using autonomous underwater vehicles (AUVs)<n>We first formulate a joint trajectory and power control optimization problem, and then present an innovative hierarchical action management framework to solve it.<n>Under the centralized training and decentralized execution paradigm, our target detection framework enables adaptive covert cooperation while satisfying both energy and mobility constraints.
  arXiv  Detail & Related papers  (2025-10-21T02:14:11Z)
• Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning [51.52387511006586]
  We propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies. HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios.
  arXiv  Detail & Related papers  (2024-06-12T08:48:06Z)
• Evolutionary Algorithms for Optimizing Emergency Exit Placement in Indoor Environments [0.0]
  A cellular-automaton model is used to simulate the behavior of pedestrians in such scenarios. A metric is proposed to determine how successful or satisfactory an evacuation was. Two metaheuristic algorithms, namely an iterated greedy and an evolutionary algorithm (EA) are proposed to solve the problem.
  arXiv  Detail & Related papers  (2024-05-28T16:50:42Z)
• Solving Expensive Optimization Problems in Dynamic Environments with Meta-learning [32.41025515064283]
  We propose a simple yet effective meta-learning-based optimization framework for solving expensive dynamic optimization problems. This framework is flexible, allowing any off-the-shelf continuously differentiable surrogate model to be used in a plug-in manner. Experiments demonstrate the effectiveness of the proposed algorithm framework compared to several state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2023-10-19T07:42:51Z)
• Federated Multi-Level Optimization over Decentralized Networks [55.776919718214224]
  We study the problem of distributed multi-level optimization over a network, where agents can only communicate with their immediate neighbors. We propose a novel gossip-based distributed multi-level optimization algorithm that enables networked agents to solve optimization problems at different levels in a single timescale. Our algorithm achieves optimal sample complexity, scaling linearly with the network size, and demonstrates state-of-the-art performance on various applications.
  arXiv  Detail & Related papers  (2023-10-10T00:21:10Z)
• AbCD: A Component-wise Adjustable Framework for Dynamic Optimization Problems [49.1574468325115]
  Dynamic Optimization Problems (DOPs) are characterized by changes in the fitness landscape that can occur at any time and are common in real world applications. We develop a component-oriented framework for DOPs called Adjustable Components for Dynamic Problems (AbCD) Our results highlight existing problems in the DOP field that need to be addressed in the future development of algorithms and components.
  arXiv  Detail & Related papers  (2023-10-09T08:11:31Z)
• Constrained Environment Optimization for Prioritized Multi-Agent Navigation [11.473177123332281]
  This paper aims to consider the environment as a decision variable in a system-level optimization problem. We propose novel problems of unprioritized and prioritized environment optimization. We show, through formal proofs, under which conditions the environment can change while guaranteeing completeness.
  arXiv  Detail & Related papers  (2023-05-18T18:55:06Z)
• Environment Optimization for Multi-Agent Navigation [11.473177123332281]
  The goal of this paper is to consider the environment as a decision variable in a system-level optimization problem. We show, through formal proofs, under which conditions the environment can change while guaranteeing completeness. In order to accommodate a broad range of implementation scenarios, we include both online and offline optimization, and both discrete and continuous environment representations.
  arXiv  Detail & Related papers  (2022-09-22T19:22:16Z)
• Optimizing Indoor Navigation Policies For Spatial Distancing [8.635212273689273]
  In this paper, we focus on the modification of policies that can lead to movement patterns and directional guidance of occupants. We show that within our framework, the simulation-optimization process can help to improve spatial distancing between agents.
  arXiv  Detail & Related papers  (2022-06-04T21:57:22Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation [84.90801699807426]
  This paper proposes an effective meta-optimization based strategy dubbed MetaAlign. We treat the domain alignment objective and the classification objective as the meta-train and meta-test tasks in a meta-learning scheme. Experimental results demonstrate the effectiveness of our proposed method on top of various alignment-based baseline approaches.
  arXiv  Detail & Related papers  (2021-03-25T03:16:05Z)
• Distributed Multi-agent Meta Learning for Trajectory Design in Wireless Drone Networks [151.27147513363502]
  This paper studies the problem of the trajectory design for a group of energyconstrained drones operating in dynamic wireless network environments. A value based reinforcement learning (VDRL) solution and a metatraining mechanism is proposed.
  arXiv  Detail & Related papers  (2020-12-06T01:30:12Z)
• The multi-objective optimisation of breakwaters using evolutionary approach [62.997667081978825]
  In engineering practice, it is often necessary to increase the effectiveness of existing protective constructions for ports and coasts. In the paper, the multi-objective evolutionary approach for the breakwaters optimisation is proposed.
  arXiv  Detail & Related papers  (2020-04-06T21:48:01Z)
• Decentralized MCTS via Learned Teammate Models [89.24858306636816]
  We present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search. We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators.
  arXiv  Detail & Related papers  (2020-03-19T13:10:20Z)
• Dynamic Federated Learning [57.14673504239551]
  Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data. Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
  arXiv  Detail & Related papers  (2020-02-20T15:00:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.