This package provides a way to develop text grammars that represent a language of interconnected 3D objects in a Python environment.

An exploration of various grass rendering techniques

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

Elias Daler's Bikeshed Renderer (Vulkan renderer/game engine)

This method takes best of both world. On one hand,it tries to reduce the overall path cost by using A-star and on other hand it reduces the time complexity by adapting real time reactive power from…

Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs

Layer-based infinite procedural generation

Official implementation for the LABOR-agent.

This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

AAGPT is another experimental open-source application showcasing the capabilities of large language models, such as GPT-3.5 and GPT-4.

A 3D Modeler Made in a Week

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

A character walking around on uneven terrain in Bullet World

Python package to simulate a virtual UAV (quadcopter) within a scene with visualizations and sensor interface such as POV camera output

MAVeric generates minimum snap trajectories for quadrotors and comes with a simple to use GUI, a visualization and simulation of the trajectory, and a CLI version.

Turn any webpage into structured data using LLMs

English to robot code

🐢 Open-Source Evaluation & Testing for LLMs and ML models

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

A flexible Multi-Agent Reinforcement Learning (MARL) environment for Collective Robotic Construction (CRC) systems

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL

A workbench for online model-free Reinforcement Learning on continuous control problems

The source code of the experiments on the paper ""Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning" (PlosONE) by Borja Fernandez-Gauna, Ismael Etxeberria…

Interactive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player characters (NPCs) in any game! 🎮🤖🚀

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

OMNI: Open-endedness via Models of human Notions of Interestingness

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…