Cognitive-AI-Systems / MAPF-GPT-DDGLinks
[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.
☆55Updated 2 weeks ago
Alternatives and similar repositories for MAPF-GPT-DDG
Users that are interested in MAPF-GPT-DDG are comparing it to the libraries listed below
Sorting:
- Code for [ICML2025]``Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design``.☆47Updated last month
- The original Shared Recurrent Memory Transformer implementation☆27Updated last week
- Model-Based Transfer Learning for Contextual Reinforcement Learning (NeurIPS 2024)☆24Updated 7 months ago
- ☆17Updated last week
- Benchmarks for Multi-Objective Multi-Agent Decision Making☆95Updated 3 weeks ago
- Repo to reproduce the First-Explore paper results☆37Updated 6 months ago
- ☆15Updated last year
- A ray-based library of Distributed POPulation-based OPtimization for Large-Scale Black-Box Optimization.☆18Updated last year
- ☆23Updated 9 months ago
- Drop-in environment replacements that make your RL algorithm train faster.☆21Updated last year
- This repository is the official implementation of the TRAC optimizer in Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement …☆28Updated 2 months ago
- BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO☆60Updated 9 months ago
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆28Updated this week
- A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks☆33Updated 8 months ago
- [AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on …☆71Updated 3 weeks ago
- How to create rational LLM-based agents? Using game-theoretic workflows!☆72Updated last month
- POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically desig…☆44Updated last week
- Implementation of Soft Actor Critic and some of its improvements in Pytorch☆60Updated 5 months ago
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning - - — ICLR 2025☆75Updated 5 months ago
- General multi-task deep RL Agent☆183Updated last year
- Simplest and Cleanest DreamerV3 implementation out there☆77Updated 4 months ago
- Exploitability calculation for imperfect-information game benchmarks☆28Updated 3 months ago
- Implementation of RL-Enabled Distributed Assignment (REDA)☆20Updated last year
- ☆49Updated last month
- Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observ…☆27Updated 3 weeks ago
- MAexp is a generic platform for RL-based multi-agent exploration☆86Updated 2 months ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆103Updated this week
- [ICLR 2025] Official implementation of DICL (Disentangled In-Context Learning), featured in the paper "Zero-shot Model-based Reinforcemen…☆22Updated 5 months ago
- ☆12Updated last year
- A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers☆53Updated 2 years ago