Awesome AI Agents › Generative Agents Simulation
The project "poke-env" is a Python interface designed to facilitate the creation and training of Reinforcement Learning (RL) bots to battle on the popular online platform Pokemon Showdown. It provides an easy-to-use environment where users can develop both rule-based and RL-based agents to simulate Pokemon battles. The core concept revolves around creating agents as Python classes that inherit from a base Player class, allowing users to define custom strategies for choosing moves and switching Pokemon during battles. The project includes comprehensive documentation and examples to help users get started quickly, including sample code for a simple agent that selects powerful moves or switches Pokemon based on their health. To use poke-env, users need Python 3.9 or higher and a running Pokemon Showdown server. While it is possible to test agents against human players on Smogon's public server, the project recommends setting up a local development server with reduced security restrictions to facilitate training and testing. Detailed setup instructions are provided in the documentation. The project also includes data files adapted from the official Pokemon Showdown data, ensuring compatibility and accuracy in battle simulations. Poke-env is open-source under the MIT license and is actively maintained with badges indicating its PyPI version, Python compatibility, documentation status, and code coverage. It originated as a follow-up to a university AI class project and draws inspiration from other Pokemon Showdown bot projects. The repository encourages citation for academic use and acknowledges the contributions of the Pokemon Showdown community and Smogon forums for data and inspiration. Overall, poke-env is a specialized tool for AI researchers, hobbyists, and developers interested in experimenting with reinforcement learning and game AI in the context of Pokemon battles, providing a robust and extensible platform for creating intelligent battle agents.
https://github.com/hsahovic/poke-env
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.