Conference item icon

Conference item

Meta-reinforcement learning for mastering multiple skills and generalizing across environments in text-based games

Abstract:

Text-based games can be used to develop task-oriented text agents for accomplishing tasks with high-level language instructions, which has potential applications in domains such as human-robot interaction. Given a text instruction, reinforcement learning is commonly used to train agents to complete the intended task owing to its convenience of learning policies automatically. However, because of the large space of combinatorial text actions, learning a policy network that generates an action ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.18653/v1/2021.metanlp-1.1

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
Publisher:
Association for Computational Linguistics
Host title:
Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing
Publication date:
2021-07-27
Acceptance date:
2021-05-31
Event title:
1st Workshop on Meta Learning and Its Applications to Natural Language Processing
Event location:
Virtual event
Event website:
https://meta-nlp-2021.github.io/
Event start date:
2021-08-05
Event end date:
2021-08-05
DOI:
Language:
English
Keywords:
Pubs id:
1200255
Local pid:
pubs:1200255
Deposit date:
2021-12-15

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP