Cognitive-AI-Systems / 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.
☆48Updated this week
Related projects: ⓘ
- MAexp is a generic platform for RL-based multi-agent exploration☆57Updated 4 months ago
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning☆36Updated last month
- ☆61Updated last week
- Official code for TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations☆18Updated 2 months ago
- Benchmarks for Multi-Objective Multi-Agent Decision Making☆51Updated last month
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code☆20Updated 3 weeks ago
- ☆17Updated 3 months ago
- ☆11Updated 2 months ago
- Repo to reproduce the First-Explore paper results☆36Updated last year
- Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"☆30Updated 11 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆41Updated 3 months ago
- Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observ…☆25Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆73Updated 2 months ago
- The official implementation of the paper "Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction".☆32Updated 7 months ago
- ☆22Updated last month
- Explainable Reinforcement Learning (XRL) Resources☆33Updated last week
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆37Updated 3 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated last month
- Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC☆50Updated last year
- Repository for "Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics" …☆12Updated 3 months ago
- Gradient Boosting Reinforcement Learning☆75Updated last week
- We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effe…☆17Updated 7 months ago
- Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"☆69Updated 7 months ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆34Updated 9 months ago
- ☆12Updated 11 months ago
- This repository contains a deep learning-based approach for improving A* search efficiency on grid graphs. By learning instance-dependent…☆22Updated 3 weeks ago
- General multi-task deep RL Agent☆158Updated 3 months ago
- Official code for "Reward-Free Curricula for Training Robust World Models", ICLR 2024.☆25Updated 7 months ago
- Official code for "World Models via Policy-Guided Trajectory Diffusion", TMLR 2024☆53Updated 5 months ago
- Hypothetical Minds is an autonomous LLM-based agent for diverse multi-agent settings, integrating a Theory of Mind module Theory of Mind …☆16Updated 2 months ago