search

QuangBK / generativeAgent_LLM

Implementation of "Generative Agents: Interactive Simulacra of Human Behavior" paper with Guidance and Langchain. Full features and work with local LLMs.
Other
271 stars 36 forks source link

Loop #7

Closed chris-aeviator closed 1 year ago

chris-aeviator commented 1 year ago

Did you start working on the idea of the "simulation loop"? What I don't get from the paper (where they also have spatial movement): is there a world-state including a world tick, or how would the loop look like, do agents decide what to do next (reflect, obsever, ...) or is this a pre-programmed script when implemented.

grafik

QuangBK commented 1 year ago

Hi, for making the one like the original paper, we need to have a simulation environment (they did with Phaser) so the agents can interact with it. In my implementation, only the agent functions are provided but not the 'loop logic' (since I don't have the environment). Hope that someone can make a simulation environment for it :)