Augmenting Autotelic Agents with Large Language Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Augmenting Autotelic Agents with Large Language Models

Abstract

Humans learn to master open-ended repertoires of skills by imagining and practicing their own goals. This autotelic learning process, literally the pursuit of self-generated (auto) goals (telos), becomes more and more open-ended as the goals become more diverse, abstract and creative. The resulting exploration of the space of possible skills is supported by an inter-individual exploration: goal representations are culturally evolved and transmitted across individuals, in particular using language. Current artificial agents mostly rely on predefined goal representations corresponding to goal spaces that are either bounded (e.g. list of instructions), or unbounded (e.g. the space of possible visual inputs) but are rarely endowed with the ability to reshape their goal representations, to form new abstractions or to imagine creative goals. In this paper, we introduce a language model augmented autotelic agent (LMA3) that leverages a pretrained language model (LM) to support the representation, generation and learning of diverse, abstract, human-relevant goals. The LM is used as an imperfect model of human cultural transmission; an attempt to capture aspects of humans' common-sense, intuitive physics and overall interests. Specifically, it supports three key components of the autotelic architecture: 1) a relabeler that describes the goals achieved in the agent's trajectories, 2) a goal generator that suggests new high-level goals along with their decomposition into subgoals the agent already masters, and 3) reward functions for each of these goals. Without relying on any hand-coded goal representations, reward functions or curriculum, we show that LMA3 agents learn to master a large diversity of skills in a task-agnostic text-based environment.
Fichier principal
Vignette du fichier
_CoLLAs_2023__Augmenting_Autotelic_Agents_with_Large_Language_Models_Towards_Open_Ended_Skill_Discovery-1.pdf (1.99 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04375117 , version 1 (05-01-2024)

Identifiers

  • HAL Id : hal-04375117 , version 1

Cite

Cédric Colas, Laetitia Teodorescu, Pierre-Yves Oudeyer, Eric Xingdi Yuan, Marc-Alexandre Côté. Augmenting Autotelic Agents with Large Language Models. CoLLAs 2023 - Conference on Lifelong Learing Agents, Aug 2023, Montreal, Canada. ⟨hal-04375117⟩

Collections

INRIA INRIA2
11 View
25 Download

Share

Gmail Facebook X LinkedIn More