Grounding Language for Transfer in Deep Reinforcement Learning release_atofepyaobgd3jckvgonompkxy

by Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

Published in The Journal of Artificial Intelligence Research by AI Access Foundation.

2018   Volume 63, p849-874

Abstract


 
 
 In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, learning generalized policy representations that work across domains remains a challenging problem. We demonstrate that textual descriptions of environments provide a compact intermediate channel to facilitate effective policy transfer. Specifically, by learning to ground the meaning of text to the dynamics of the environment such as transitions and rewards, an autonomous agent can effectively bootstrap policy learning on a new domain given its description. We employ a model-based RL approach consisting of a differentiable planning module, a model-free component and a factorized state representation to effectively use entity descriptions. Our model outperforms prior work on both transfer and multi-task scenarios in a variety of different environments. For instance, we achieve up to 14% and 11.5% absolute improvement over previously existing models in terms of average and initial rewards, respectively.
 
 
In application/xml+jats format

Archived Files and Locations

application/pdf  2.5 MB
file_hm44kdlaf5bmtpck52uos5ux2q
jair.org (publisher)
web.archive.org (webarchive)
application/pdf  2.7 MB
file_6j2elkyaxvbllkeq3sjf3obpdm
dspace.mit.edu (web)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2018-12-19
Journal Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
Not in Keepers Registry
ISSN-L:  1076-9757
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5387564b-d4ad-460a-ba7e-37958b3a9ea8
API URL: JSON