IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL

2023-06-20 · NeurIPS 2023 11 · Pascal Leroy, Pablo G. Morato, Jonathan Pisane, Athanasios Kolios, Damien Ernst

We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform for benchmarking the scalability of cooperative MARL methods in real-world engineering applications. In IMP, a multi-component engineering system is subject to a risk of failure due to its components' damage condition. Specifically, each agent plans inspections and repairs for a specific system component, aiming to minimise maintenance costs while cooperating to minimise system failure risk. With IMP-MARL, we release several environments including one related to offshore wind structural systems, in an effort to meet today's needs to improve management strategies to support sustainable and reliable energy systems. Supported by IMP practical engineering environments featuring up to 100 agents, we conduct a benchmark campaign, where the scalability and performance of state-of-the-art cooperative MARL methods are compared against expert-based heuristic policies. The results reveal that centralised training with decentralised execution methods scale better with the number of agents than fully centralised or decentralised RL approaches, while also outperforming expert-based heuristic policies in most IMP environments. Based on our findings, we additionally outline remaining cooperation and scalability challenges that future MARL methods should still address. Through IMP-MARL, we encourage the implementation of new environments and the further development of MARL methods.

📄 PDF Abstract BibTeX arXiv:2306.11551

Code (1)

moratodpg/imp_marl 공식 구현 pytorch

Tasks

Benchmarking Management Multi-agent Reinforcement Learning

Turn-based Multi-Agent Reinforcement Learning Model Checking

2025-01-06 · Dennis Gross

In this paper, we propose a novel approach for verifying the compliance of turn-based multi-agent reinforcement learning (TMARL) agents with complex requirements in stochastic multiplayer games. Our method overcomes the …

model Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Agent Environment Cycle Games

2020-09-28 · Justin K. Terry, Nathaniel Grammel, Benjamin Black, Ananth Hari 외

Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL). We argue that the POSG model is conceptually ill suited to software MARL env…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

SandboxEval: Towards Securing Test Environment for Untrusted Code

2025-03-27 · Rafiqul Rabin, Jesse Hostetler, Sean McGregor, Brett Weir 외

While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code. Testing LLM-generated code therefore poses significant risks to assessment infrastructure tasked with…

Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning

2026-02-10 · Zhida Jiang, Zhaolong Xing, Jiawei Lu, Yipei Niu 외 arxiv

Despite algorithm-level innovations for multi-agent reinforcement learning (MARL), the underlying networked infrastructure for large-scale MARL training remains underexplored. Existing training frameworks primarily optim…

Multi-agent Reinforcement Learning

Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning

2025-09-20 · Wei Duan, Jie Lu, Junyu Xuan arxiv

In networked multi-agent reinforcement learning (Networked-MARL), decentralized agents must act under local observability and constrained communication over fixed physical graphs. Existing methods often assume static nei…