Skip to content

PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3

Aug 2026 · arXiv.org · Vol abs/2608.04905 · 1 citation · 61 references
Computer Science

TL;DR

The resulting framework combines learned exploration with structured expert guidance without requiring LaCAM3 at inference and substantially outperforms state-of-the-art learning-based baselines and scales to ultra-large instances with up to city-level 100,000 agents.

Abstract

We present PRIMAL3, an ultra-large-scale learning-based framework for multi-agent pathfinding (MAPF) that integrates reinforcement learning, topology-aware communication, LaCAM3-guided training, and PIBT-based action refinement. PRIMAL3 targets failures at topologically critical states, where agents must coordinate decisively around bottlenecks, dead ends, and persistent conflicts. Each agent is represented using features derived from cut vertices, dead-end regions, shortest-path distances, and blocking estimates. Two complementary graphs capture agent interactions: a same-direction following graph propagates multihop context along compatible paths, while a different-direction conflict graph differentiates agents competing for shared space through masked attention and relative features. During training, we propose to let policy entropy identify uncertain agents, for which LaCAM3 provides confidence-triggered action interventions and label-smoothed imitation targets. During execution, a priority-aware PIBT module refines the proposed joint actions using persistent, learned, and distance-aware priorities together with policy-aware fallback preferences while maintaining collision-free execution. The resulting framework combines learned exploration with structured expert guidance without requiring LaCAM3 at inference. Experiments demonstrate that PRIMAL3 substantially outperforms state-of-the-art learning-based baselines and scales to ultra-large instances with up to city-level 100,000 agents. Real-world experiments further demonstrate the feasibility of deploying PRIMAL3 on physical robotic systems and ablation studies validate the individual contributions the components we proposed. Project page: https://marmotlab.github.io/PRIMAL3/

View source

Similar papers

Conference Sep 2026

Curriculum-guided decentralized deep Q-network for multi-agent pathfinding under intermittent obstacles

Multi-agent pathfinding (MAPF) requires multiple agents to reach assigned goals while avoiding vertex, edge, and intermittent-obstacle conflicts in a shared workspace. Learning-based MAPF is attractive for online decision-making, but fully decentralized reinforcement learning remains vulnerable to sparse rewards, non-s...

Ji-Cai Wang, Yu-Ting Guo, Meng-Yao Zhang et al. · 0 citations
#artificial intelligence Preprint Nov 2026

Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration

EFXPLORER is proposed, a constrained exploration framework that maximizes exploration objectives subject to a constraint that preserves established task performance and incorporates a successor distance-based intrinsic reward that captures long-horizon dependencies.

Sungil Son, Hoseong Jung, Dahyun Oh et al. · 0 citations
Open access 2026

LYCO: Learning to Yield for Decentralized Multi-Agent Path Finding in Congested Environments

In grid-world settings, LYCO consistently outperformed representative decentralized RL baselines in high-density environments, achieving a success rate above 0.7 at an agent density of 0.3 on a $20\times 20$ map with obstacle density 0.1 while maintaining a competitive makespan.

Hiroya Makino, Koji Noshiro, Koji Hasebe et al. · 0 citations

Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding

Results show that round-level intent refinement can improve joint-action coordination while preserving decentralized execution, and DMM, the Decentralized Master-Mind, achieves higher success rates and lower solution costs than the evaluated learnable baselines.

Valeriy Vyaltsev, A. Andreychuk, T. Zlotnikova et al. · 1 citation
Preprint Oct 2026

Map-Distribution Mixture-of-Experts for Multi-Agent Pathfinding

This study explores a meta-level Mixture-of-Experts (MoE) approach to learning-based MAPF, where given a collection of compact yet high-performing experts specialised for different map distributions, the architecture learns a router that selectively fuses their outputs according to each agent's local situation.

Fumimaro Suzuki, Keisuke Okumura · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.