Awesome AI Agents › Generative Agents Simulation
PyGame Learning Environment (PLE) is a Python-based reinforcement learning environment designed to facilitate the development and testing of reinforcement learning algorithms. It mimics the interface of the Arcade Learning Environment, providing a familiar and accessible platform for practitioners to focus on designing models and experiments rather than building environments from scratch. PLE aims to build a comprehensive library of games that can be used for reinforcement learning research and experimentation. The environment supports various games, with Pong being one example, and allows users to easily integrate their own agents to interact with these games. The framework provides control methods for games and supports interaction through a simple API, enabling agents to receive observations, take actions, and receive rewards. PLE is designed to be user-friendly, with options to display the game screen or run in headless mode for environments without a graphical display. It requires dependencies such as numpy, pygame, and pillow, and can be installed via pip after cloning the repository. The project is actively maintained with ongoing work on documentation, testing, parallel learning capabilities, and expanding the game library. PLE is suitable for researchers and developers interested in reinforcement learning, providing a practical and extensible platform for experimentation and development. The project encourages contributions, especially in adding new games, and offers detailed documentation and examples to help users get started quickly. Overall, PLE is a valuable tool for advancing reinforcement learning research by simplifying environment setup and providing a diverse set of game scenarios for training and evaluation.
https://github.com/ntasfi/PyGame-Learning-Environment
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.
A locally runnable, low-cost implementation of generative agents simulating human-like behavior in an interactive Dungeons & Dragons setting using large language models.
GPTRPG is a proof-of-concept project featuring a GPT-based AI agent that autonomously interacts within a simple RPG-like environment using the OpenAI API.