Awesome AI Agents › Generative Agents Simulation
ChatSim is a project focused on editable scene simulation for autonomous driving through collaboration with large language model (LLM) agents. It is highlighted as a CVPR 2024 notable work and aims to provide a sophisticated simulation environment that integrates advanced rendering techniques and AI-driven scene editing capabilities. The project supports two main background rendering engines: McNeRF, which encodes exposure time for brightness-consistent rendering, and 3D Gaussian Splatting, which offers significantly faster rendering speeds and higher PSNR in training views but may introduce artifacts under strong perspective shifts. The system leverages Blender for 3D rendering and includes tools for video and image inpainting to enhance scene editing. It also supports trajectory tracking for smoother and more realistic motion simulation, using a reinforcement learning-based module. The project requires Ubuntu 20.04 or higher, Python 3.8+, PyTorch 1.13+, and CUDA 11.6+, with optional dependencies like COLMAP or Metashape for pose recalibration and OpenAI API or NVIDIA AI models for LLM integration. Installation involves setting up the environment, choosing and installing a background rendering engine, configuring inpainting tools, installing Blender and its utilities, and optionally setting up trajectory tracking and skydome lighting training modules. The project is designed to work with the Waymo Open Dataset for autonomous driving data and provides detailed instructions for data preparation and usage. ChatSim aims to facilitate editable and realistic scene simulations that can be used for autonomous driving research and development, enabling users to manipulate and simulate complex driving scenarios with high fidelity and AI assistance.
https://github.com/yifanlu0227/ChatSim
This project provides a simulation framework for generative agents that mimic believable human behaviors within an interactive game environment, enabling running, saving, replaying, and demonstrating agent-based simulations.
Voyager is an open-ended embodied agent powered by large language models that autonomously explores and learns diverse skills in Minecraft through lifelong learning and an evolving skill library.
SFighterAI is a deep reinforcement learning-based AI agent designed to master and beat the final boss in Street Fighter II: Special Champion Edition using only game screen pixel data.
A comprehensive Godot framework for creating smooth and complex AI motion using steering behaviors in both 2D and 3D games.
WorldX turns a single sentence into a running simulated world, generating maps and characters with LLMs and letting autonomous agents act, remember and form stories inside it.
Control room for LLM agent societies: pause and scrub a running simulation, question individual residents, inject instructions into the next step, and export replayable experiment packs.
PyGame Learning Environment (PLE) is a Python-based reinforcement learning platform that provides a variety of games and tools to facilitate the development and testing of reinforcement learning algorithms.
A locally runnable, low-cost implementation of generative agents simulating human-like behavior in an interactive Dungeons & Dragons setting using large language models.