{"data":{"full_name":"Cognitive-AI-Systems/MAPF-GPT-DDG","name":"MAPF-GPT-DDG","description":"[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.","stars":61.0,"forks":7.0,"language":"Python","license":"MIT","archived":0.0,"subcategory":"mathematical-reasoning-transformers","last_pushed_at":"2026-02-21T20:52:47+00:00","pypi_package":null,"npm_package":null,"downloads_monthly":0.0,"dependency_count":0.0,"commits_30d":null,"reverse_dep_count":0.0,"maintenance_score":10.0,"adoption_score":8.0,"maturity_score":16.0,"community_score":12.0,"quality_score":46.0,"quality_tier":"emerging","risk_flags":"['no_package', 'no_dependents']"},"meta":{"timestamp":"2026-04-14T22:01:24.067386+00:00"}}