Stars
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
POMG algorithm for large-scale pursuit game with partial observation and no communication.
Multi-Agent RL for UAV Control for Fair and Energy-Efficient Coverage Maximisation
Monitoring recent cross-research on LLM & RL on arXiv for control. If there are good papers, PRs are welcome.
A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".
UAV Flocking with Multi-Agent Reinforcement Learning. The Code of the paper: "An invulnerable leader–follower collision-free unmanned aerial vehicle flocking system with attention-based Multi-Agent…
The Drone Swarm Search project provides an environment for SAR missions built on PettingZoo, where agents, represented by drones, are tasked with locating targets identified as shipwrecked individu…
[ICCC 2025] UavNetSim-v1: A Python-based simulation platform for designing and testing communication protocols and control algorithms in UAV swarm.
We proposed to explore and search for the target in unknown environment based on Large Language Model for multi-robot system.
This is the official implementation of Multi-Agent PPO (MAPPO).
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
A drone swarm simulator based on ROS (Robot Operating System).
FlockGPT is a novel approach to drone flocking control using natural language and generative AI. It features an LLM-based interface for user interaction and a flocking technology system that ensure…
Community for applying LLMs to robotics and a robot simulator with ChatGPT integration
An environment based on JSBSIM aimed at one-to-one close air combat.
Survey of Small Language Models from Penn State, ...
Minecraft AI with LLMs+Mineflayer
The main repository for the development of the evolution game Thrive.
This is the official implementation of the paper "DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy".
Open-ended wargames with large language models
The data preprocessing code for FIREBALL
Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.