@inproceedings{sharma-etal-2022-skill,
title = "Skill Induction and Planning with Latent Language",
author = "Sharma, Pratyusha and
Torralba, Antonio and
Andreas, Jacob",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.120",
doi = "10.18653/v1/2022.acl-long.120",
pages = "1713--1726",
abstract = "We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level sub-tasks, using only a small number of seed annotations to ground language in action. In trained models, natural language commands index a combinatorial library of skills; agents can use these skills to plan by generating high-level instruction sequences tailored to novel goals. We evaluate this approach in the ALFRED household simulation environment, providing natural language annotations for only 10{\%} of demonstrations. It achieves performance comparable state-of-the-art models on ALFRED success rate, outperforming several recent methods with access to ground-truth plans during training and evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2022-skill">
<titleInfo>
<title>Skill Induction and Planning with Latent Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pratyusha</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Torralba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Andreas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level sub-tasks, using only a small number of seed annotations to ground language in action. In trained models, natural language commands index a combinatorial library of skills; agents can use these skills to plan by generating high-level instruction sequences tailored to novel goals. We evaluate this approach in the ALFRED household simulation environment, providing natural language annotations for only 10% of demonstrations. It achieves performance comparable state-of-the-art models on ALFRED success rate, outperforming several recent methods with access to ground-truth plans during training and evaluation.</abstract>
<identifier type="citekey">sharma-etal-2022-skill</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.120</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.120</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1713</start>
<end>1726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Skill Induction and Planning with Latent Language
%A Sharma, Pratyusha
%A Torralba, Antonio
%A Andreas, Jacob
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F sharma-etal-2022-skill
%X We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level sub-tasks, using only a small number of seed annotations to ground language in action. In trained models, natural language commands index a combinatorial library of skills; agents can use these skills to plan by generating high-level instruction sequences tailored to novel goals. We evaluate this approach in the ALFRED household simulation environment, providing natural language annotations for only 10% of demonstrations. It achieves performance comparable state-of-the-art models on ALFRED success rate, outperforming several recent methods with access to ground-truth plans during training and evaluation.
%R 10.18653/v1/2022.acl-long.120
%U https://aclanthology.org/2022.acl-long.120
%U https://doi.org/10.18653/v1/2022.acl-long.120
%P 1713-1726
Markdown (Informal)
[Skill Induction and Planning with Latent Language](https://aclanthology.org/2022.acl-long.120) (Sharma et al., ACL 2022)
ACL
- Pratyusha Sharma, Antonio Torralba, and Jacob Andreas. 2022. Skill Induction and Planning with Latent Language. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1713–1726, Dublin, Ireland. Association for Computational Linguistics.