LLM-POET: Evolving Complex Environments using Large Language Models

TL;DR

This paper introduces LLM-POET, a novel approach that uses large language models to generate and mutate complex environments for co-evolving agents, significantly enhancing diversity and performance in open-ended AI systems.

Contribution

It presents a new method combining LLMs with POET to improve environment complexity and diversity, leading to better agent skill development.

Findings

34% increase in performance gain over previous methods

LLM-generated environments are more diverse and complex

Agents learn a broader set of skills from richer environments

Abstract

Creating systems capable of generating virtually infinite variations of complex and novel behaviour without predetermined goals or limits is a major challenge in the field of AI. This challenge has been addressed through the development of several open-ended algorithms that can continuously generate new and diverse behaviours, such as the POET and Enhanced-POET algorithms for co-evolving environments and agent behaviour. One of the challenges with existing methods however, is that they struggle to continuously generate complex environments. In this work, we propose LLM-POET, a modification of the POET algorithm where the environment is both created and mutated using a Large Language Model (LLM). By fine-tuning a LLM with text representations of Evolution Gym environments and captions that describe the environment, we were able to generate complex and diverse environments using natural language. We found that not only could the LLM produce a diverse range of environments, but compared to the CPPNs used in Enhanced-POET for environment generation, the LLM allowed for a 34% increase in the performance gain of co-evolution. This increased performance suggests that the agents were able to learn a more diverse set of skills by training on more complex environments.