Self-imitation Learning for Action Generation in Text-based Games

Shi, Z; Xu, Y; Fang, M; Chen, L

Self-imitation Learning for Action Generation in Text-based Games

Shi, Z Xu, Y Fang, M Chen, L

Permalink

Publication Type:: Conference Proceeding
Citation:: EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 2023, pp. 703-726
Issue Date:: 2023-01-01

Recently Added

	Filename	Description	Size
	2023.eacl-main.50.pdf	Published version	4.1 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Shi, Z
dc.contributor.author	Xu, Y
dc.contributor.author	Fang, M
dc.contributor.author	Chen, L https://orcid.org/0000-0002-6468-5729
dc.date.accessioned	2024-03-04T22:41:31Z
dc.date.available	2024-03-04T22:41:31Z
dc.date.issued	2023-01-01
dc.identifier.citation	EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 2023, pp. 703-726
dc.identifier.isbn	9781959429449
dc.identifier.uri	http://hdl.handle.net/10453/176091
dc.description.abstract	In this work, we study reinforcement learning (RL) in solving text-based games. We address the challenge of combinatorial action space, by proposing a confidence-based self-imitation model to generate action candidates for the RL agent. Firstly, we leverage the self-imitation learning to rank and exploit past valuable trajectories to adapt a pre-trained language model (LM) towards a target game. Then, we devise a confidence-based strategy to measure the LM's confidence with respect to a state, thus adaptively pruning the generated actions to yield a more compact set of action candidates. In multiple challenging games, our model demonstrates promising performance in comparison to the baselines.
dc.language	en
dc.relation	Facebook
dc.relation.ispartof	EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	Self-imitation Learning for Action Generation in Text-based Games
dc.type	Conference Proceeding
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	recently_added	*
dc.date.updated	2024-03-04T22:41:28Z
pubs.publication-status	Published

Abstract:

In this work, we study reinforcement learning (RL) in solving text-based games. We address the challenge of combinatorial action space, by proposing a confidence-based self-imitation model to generate action candidates for the RL agent. Firstly, we leverage the self-imitation learning to rank and exploit past valuable trajectories to adapt a pre-trained language model (LM) towards a target game. Then, we devise a confidence-based strategy to measure the LM's confidence with respect to a state, thus adaptively pruning the generated actions to yield a more compact set of action candidates. In multiple challenging games, our model demonstrates promising performance in comparison to the baselines.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176091