CognitiveAISystems / MAPF-GPT
This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced by LaCAM, it generates collision-free paths under partial observability without heuristics or agent communication. MAPF-GPT excels on unseen instances and outperforms state-of-the-art solvers.
☆34Updated 3 weeks ago
Alternatives and similar repositories for MAPF-GPT:
Users that are interested in MAPF-GPT are comparing it to the libraries listed below
- POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically desig…☆21Updated this week
- [IROS 2024] EPH: Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding☆32Updated 3 months ago
- ☆20Updated last month
- Minimal Python implementation of LaCAM* for MAPF☆17Updated 5 months ago
- ☆12Updated 3 months ago
- offical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'☆41Updated last year
- PPO and PyMARL baseline for Pogema environment☆20Updated 4 months ago
- Learning Selective Communication for Multi-Agent Path Finding☆25Updated 3 years ago
- Neural Potential Field for Obstacle-Aware Local Motion Planning☆17Updated 7 months ago
- Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding (AIJ-22)☆64Updated 4 months ago
- Minimal Python implementation of PIBT for MAPF☆21Updated last year
- Codes for paper Integrated Task Assignment and Path Planning forCapacitated Multi-Agent Pickup and Delivery☆40Updated 2 years ago
- Official implementation of the paper "Multi-Robot Coordination and Layout Design for Automated Warehousing", published in IJCAI 2023.☆20Updated last year
- Engineering LaCAM*: Towards Real-Time, Large-Scale, and Near-Optimal Multi-Agent Pathfinding (AAMAS-24)☆57Updated 3 months ago
- Distributed Heuristic Multi-Agent Path Finding with Communication - ICRA 2021☆63Updated 3 years ago
- Solution of NeurIPS 2020 Flatland Challenge from the team An_old_driver.☆58Updated 3 years ago
- Learnable MAPF. “Distributed Heuristic Multi-Agent Path Finding with Communication” (DHC) algorithm from ICRA 2021 is implemented and ben…☆18Updated last year
- python implementation of "Multi-Goal Multi-Agent Pickup and Delivery"☆8Updated last year
- MAPF-LNS2: Fast Repairing for Multi-Agent Path Finding via Large Neighborhood Search☆67Updated 8 months ago
- Implementations of various algorithms used to solve the problem of Multi-Agent Pickup and Delivery (a generalization of Multi-Agent Path …☆55Updated 3 years ago
- The official repo for ICRA 2023 paper 'Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimality'☆18Updated last year
- CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces (AAMAS-22)☆33Updated 2 years ago
- Heuristic Search vs. Learning. "Distributed Heuristic Multi-Agent Path Finding with Communication" reproduced, trained & benchmarked with…☆19Updated 2 years ago