Accès ouvert · CC BY

Policy-based Reinforcement Learning for Generalisation in Interactive Text-based Environments

Article scientifique 2023 Sciences mathématiques et statistiques Anglais

Résumé

Text-based environments enable RL agents to learn to converse and perform interactive tasks through natural language.However, previous RL approaches applied to text-based environments show poor performance when evaluated on unseen games.This paper investigates the improvement of generalisation performance through the simple switch from a value-based update method to a policy-based one, within text-based environments.We show that by replacing commonly used value-based methods with REINFORCE with baseline, a far more general agent is produced.The policy-based agent is evaluated on Coin Collector and Question Answering with interactive text (QAit), two text-based environments designed to test zero-shot performance.We see substantial improvements on a variety of zero-shot evaluation experiments, including tripling accuracy on various QAit benchmark configurations.The results indicate that policy-based RL has significantly better generalisation capabilities than value-based methods within such text-based environments, suggesting that RL agents could be applied to more complex natural language environments.

Citer ce document

Toledo, E., Buys, J., & Shock, J. P. (2023). Policy-based Reinforcement Learning for Generalisation in Interactive Text-based Environments. https://doi.org/10.18653/v1/2023.eacl-main.88

Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)

Accès au document

Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter

Voir l'article sur le site de la revue

Licence et provenance

Licence : CC BY

Notice moissonnée depuis OpenAlex le 10/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →

Statistiques

Consultations (hors robots) : 11

Téléchargements (hors robots) : 0

Méthode de comptage