@inproceedings{tan-etal-2019-learning,
title = "Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout",
author = "Tan, Hao and
Yu, Licheng and
Bansal, Mohit",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1268",
doi = "10.18653/v1/N19-1268",
pages = "2610--2621",
abstract = "A grand goal in AI is to build a robot that can accurately navigate based on natural language instructions, which requires the agent to perceive the scene, understand and ground language, and act in the real-world environment. One key challenge here is to learn to navigate in new environments that are unseen during training. Most of the existing approaches perform dramatically worse in unseen environments as compared to seen ones. In this paper, we present a generalizable navigational agent. Our agent is trained in two stages. The first stage is training via mixed imitation and reinforcement learning, combining the benefits from both off-policy and on-policy optimization. The second stage is fine-tuning via newly-introduced {`}unseen{'} triplets (environment, path, instruction). To generate these unseen triplets, we propose a simple but effective {`}environmental dropout{'} method to mimic unseen environments, which overcomes the problem of limited seen environment variability. Next, we apply semi-supervised learning (via back-translation) on these dropout environments to generate new paths and instructions. Empirically, we show that our agent is substantially better at generalizability when fine-tuned with these triplets, outperforming the state-of-art approaches by a large margin on the private unseen test set of the Room-to-Room task, and achieving the top rank on the leaderboard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2019-learning">
<titleInfo>
<title>Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Licheng</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A grand goal in AI is to build a robot that can accurately navigate based on natural language instructions, which requires the agent to perceive the scene, understand and ground language, and act in the real-world environment. One key challenge here is to learn to navigate in new environments that are unseen during training. Most of the existing approaches perform dramatically worse in unseen environments as compared to seen ones. In this paper, we present a generalizable navigational agent. Our agent is trained in two stages. The first stage is training via mixed imitation and reinforcement learning, combining the benefits from both off-policy and on-policy optimization. The second stage is fine-tuning via newly-introduced ‘unseen’ triplets (environment, path, instruction). To generate these unseen triplets, we propose a simple but effective ‘environmental dropout’ method to mimic unseen environments, which overcomes the problem of limited seen environment variability. Next, we apply semi-supervised learning (via back-translation) on these dropout environments to generate new paths and instructions. Empirically, we show that our agent is substantially better at generalizability when fine-tuned with these triplets, outperforming the state-of-art approaches by a large margin on the private unseen test set of the Room-to-Room task, and achieving the top rank on the leaderboard.</abstract>
<identifier type="citekey">tan-etal-2019-learning</identifier>
<identifier type="doi">10.18653/v1/N19-1268</identifier>
<location>
<url>https://aclanthology.org/N19-1268</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2610</start>
<end>2621</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
%A Tan, Hao
%A Yu, Licheng
%A Bansal, Mohit
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F tan-etal-2019-learning
%X A grand goal in AI is to build a robot that can accurately navigate based on natural language instructions, which requires the agent to perceive the scene, understand and ground language, and act in the real-world environment. One key challenge here is to learn to navigate in new environments that are unseen during training. Most of the existing approaches perform dramatically worse in unseen environments as compared to seen ones. In this paper, we present a generalizable navigational agent. Our agent is trained in two stages. The first stage is training via mixed imitation and reinforcement learning, combining the benefits from both off-policy and on-policy optimization. The second stage is fine-tuning via newly-introduced ‘unseen’ triplets (environment, path, instruction). To generate these unseen triplets, we propose a simple but effective ‘environmental dropout’ method to mimic unseen environments, which overcomes the problem of limited seen environment variability. Next, we apply semi-supervised learning (via back-translation) on these dropout environments to generate new paths and instructions. Empirically, we show that our agent is substantially better at generalizability when fine-tuned with these triplets, outperforming the state-of-art approaches by a large margin on the private unseen test set of the Room-to-Room task, and achieving the top rank on the leaderboard.
%R 10.18653/v1/N19-1268
%U https://aclanthology.org/N19-1268
%U https://doi.org/10.18653/v1/N19-1268
%P 2610-2621
Markdown (Informal)
[Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://aclanthology.org/N19-1268) (Tan et al., NAACL 2019)
ACL