Awesome AI Agents › Generative Agents Simulation
Suspicion-Agent is a project that implements the concepts from the research paper "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4." The project focuses on developing an agent capable of playing imperfect information games by leveraging a theory of mind approach integrated with GPT-4. Imperfect information games are those where players have incomplete knowledge about the game state, requiring strategic reasoning about opponents' beliefs and intentions. This agent uses advanced AI techniques to model and predict other players' behaviors, enhancing decision-making in such complex environments. The repository includes code for training and evaluating the agent against baseline models such as CFR (Counterfactual Regret Minimization), NFSP (Neural Fictitious Self-Play), DQN (Deep Q-Network), and DMC (Deep Monte Carlo). It provides detailed instructions for setup, including package installation and OpenAI API key configuration. The project also offers visualizations and demos hosted on Hugging Face Spaces, allowing users to interact with the agent and observe game data replays. The implementation is supported by figures illustrating the methodology, including counterfactual reasoning and theory of mind modeling. Sample outputs demonstrate the agent's gameplay and decision-making process. The project is based on the SkyAGI framework and acknowledges its authors. It is a significant contribution to AI research in game theory, particularly in applying large language models like GPT-4 to strategic game playing with imperfect information. Overall, Suspicion-Agent represents a cutting-edge integration of theory of mind concepts with state-of-the-art AI models to tackle the challenges of imperfect information games, providing tools for training, evaluation, and visualization of agent performance.
https://github.com/CR-Gjx/Suspicion-Agent
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.