Accès ouvert

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

Article scientifique 2023 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. (2023). Policy-based Reinforcement Learning for Generalisation in Interactive Text-based Environments. https://doi.org/10.18653/v1/2023.eacl-main.88

Accès au document

Ce lien n'est plus accessible actuellement. Contactez l'institution d'origine.

Auteur(s)

Edan Toledo Jan Buys Jonathan P. Shock

Statistiques

Consultations : 1

Téléchargements : 0