WS

“Westworld” simulation

“Westworld” simulation

“Westworld” simulation

A multi-agent environment simulation library
A multi-agent environment simulation library

General purpose, Multi-agent

General purpose, Multi-agent

About

  • Researchers from Stanford and Google created an interactive sandbox env with 25 Gen AI agents can simulate human behavior

  • They walk in the park, join for coffee at a cafe, and share news with colleagues. They demonstrated surprisingly good social

  • Westworld's inspiration is drawn from Unity software and Unity ML Agents, adapted in Python

  • Languages

  • Features

    • Easy creation of Grid and non-grid environments

    • Objects (Agents, Obstacles, Collectibles, Triggers)

    • Subclassing of different objects to create custom objects

    • Spawner to generate objects randomly in the environment

    • Basic rigid body system for all objects

    • Simple agent behaviors (pathfinding, wandering, random walk, fleeing, vision range)

    • Automatic maze generation

    • Layer integration to convert image to obstacle and snap it to a grid

    • Sample simulations and sample agents for classic simulations

    • Simulation visualization, replay and export (gif or video)

Links

  • GitHub

  • Documentation

  • Underlying paper - Generative Agents

  • A paper simulating interactions between tens of agents

  • Presenting an architecture that extends a language model to store and synthesize the agent's experiences, enabling dynamic behavior planning in an interactive sandbox environment with generative agents

Request product update