VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation
In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator. Specifically, we build on the concept of Universal Successor Features with an A3C agent. We introduce the novel archi...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Siriwardhana, Shamane Weerasakera, Rivindu Matthies, Denys J. C Nanayakkara, Suranga |
| description | In this paper, we show how novel transfer reinforcement learning techniques
can be applied to the complex task of target driven navigation using the
photorealistic AI2THOR simulator. Specifically, we build on the concept of
Universal Successor Features with an A3C agent. We introduce the novel
architectural contribution of a Successor Feature Dependant Policy (SFDP) and
adopt the concept of Variational Information Bottlenecks to achieve state of
the art performance. VUSFA, our final architecture, is a straightforward
approach that can be implemented using our open source repository. Our approach
is generalizable, showed greater stability in training, and outperformed recent
approaches in terms of transfer learning ability. |
| doi_str_mv | 10.48550/arxiv.1908.06376 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1908_06376</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1908_06376</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-90326957abf3279eea0857af52484cd6c554b363e5b7669b096a9301e212866c3</originalsourceid><addsrcrecordid>eNotkMFOg0AQhrl4MNUH8OS-ALiw7MB6I61oE6KJpVzJgEuzSQtklmJ9e7foaeafSb755_e8h5AHcSolf0K6mDkIFU8DDiKBW--72u_y7LlCMjiZoccj2_dm1mRdtzu3rbZ2IJZrnM6kLcvGkYaLOeHkptPAtienZ81Kwt52mtjms2Cd25VIBz2xDTlYzypjzw74jrM5LHfuvJsOj1bf_9eVV-Yv5frNLz5et-us8BES8BUXESiZYNOJKFFaI0-d6mQUp3H7Ba2UcSNAaNkkAKrhClAJHuoojFKAVqy8xz_s8nk9knNOP_U1gXpJQPwCiEVXHQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation</title><source>arXiv.org</source><creator>Siriwardhana, Shamane ; Weerasakera, Rivindu ; Matthies, Denys J. C ; Nanayakkara, Suranga</creator><creatorcontrib>Siriwardhana, Shamane ; Weerasakera, Rivindu ; Matthies, Denys J. C ; Nanayakkara, Suranga</creatorcontrib><description>In this paper, we show how novel transfer reinforcement learning techniques
can be applied to the complex task of target driven navigation using the
photorealistic AI2THOR simulator. Specifically, we build on the concept of
Universal Successor Features with an A3C agent. We introduce the novel
architectural contribution of a Successor Feature Dependant Policy (SFDP) and
adopt the concept of Variational Information Bottlenecks to achieve state of
the art performance. VUSFA, our final architecture, is a straightforward
approach that can be implemented using our open source repository. Our approach
is generalizable, showed greater stability in training, and outperformed recent
approaches in terms of transfer learning ability.</description><identifier>DOI: 10.48550/arxiv.1908.06376</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Computer Science - Neural and Evolutionary Computing ; Statistics - Machine Learning</subject><creationdate>2019-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1908.06376$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1908.06376$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Siriwardhana, Shamane</creatorcontrib><creatorcontrib>Weerasakera, Rivindu</creatorcontrib><creatorcontrib>Matthies, Denys J. C</creatorcontrib><creatorcontrib>Nanayakkara, Suranga</creatorcontrib><title>VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation</title><description>In this paper, we show how novel transfer reinforcement learning techniques
can be applied to the complex task of target driven navigation using the
photorealistic AI2THOR simulator. Specifically, we build on the concept of
Universal Successor Features with an A3C agent. We introduce the novel
architectural contribution of a Successor Feature Dependant Policy (SFDP) and
adopt the concept of Variational Information Bottlenecks to achieve state of
the art performance. VUSFA, our final architecture, is a straightforward
approach that can be implemented using our open source repository. Our approach
is generalizable, showed greater stability in training, and outperformed recent
approaches in terms of transfer learning ability.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Neural and Evolutionary Computing</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkMFOg0AQhrl4MNUH8OS-ALiw7MB6I61oE6KJpVzJgEuzSQtklmJ9e7foaeafSb755_e8h5AHcSolf0K6mDkIFU8DDiKBW--72u_y7LlCMjiZoccj2_dm1mRdtzu3rbZ2IJZrnM6kLcvGkYaLOeHkptPAtienZ81Kwt52mtjms2Cd25VIBz2xDTlYzypjzw74jrM5LHfuvJsOj1bf_9eVV-Yv5frNLz5et-us8BES8BUXESiZYNOJKFFaI0-d6mQUp3H7Ba2UcSNAaNkkAKrhClAJHuoojFKAVqy8xz_s8nk9knNOP_U1gXpJQPwCiEVXHQ</recordid><startdate>20190818</startdate><enddate>20190818</enddate><creator>Siriwardhana, Shamane</creator><creator>Weerasakera, Rivindu</creator><creator>Matthies, Denys J. C</creator><creator>Nanayakkara, Suranga</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190818</creationdate><title>VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation</title><author>Siriwardhana, Shamane ; Weerasakera, Rivindu ; Matthies, Denys J. C ; Nanayakkara, Suranga</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-90326957abf3279eea0857af52484cd6c554b363e5b7669b096a9301e212866c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Neural and Evolutionary Computing</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Siriwardhana, Shamane</creatorcontrib><creatorcontrib>Weerasakera, Rivindu</creatorcontrib><creatorcontrib>Matthies, Denys J. C</creatorcontrib><creatorcontrib>Nanayakkara, Suranga</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Siriwardhana, Shamane</au><au>Weerasakera, Rivindu</au><au>Matthies, Denys J. C</au><au>Nanayakkara, Suranga</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation</atitle><date>2019-08-18</date><risdate>2019</risdate><abstract>In this paper, we show how novel transfer reinforcement learning techniques
can be applied to the complex task of target driven navigation using the
photorealistic AI2THOR simulator. Specifically, we build on the concept of
Universal Successor Features with an A3C agent. We introduce the novel
architectural contribution of a Successor Feature Dependant Policy (SFDP) and
adopt the concept of Variational Information Bottlenecks to achieve state of
the art performance. VUSFA, our final architecture, is a straightforward
approach that can be implemented using our open source repository. Our approach
is generalizable, showed greater stability in training, and outperformed recent
approaches in terms of transfer learning ability.</abstract><doi>10.48550/arxiv.1908.06376</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1908.06376 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1908_06376 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Learning Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning |
| title | VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T02%3A59%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=VUSFA:Variational%20Universal%20Successor%20Features%20Approximator%20to%20Improve%20Transfer%20DRL%20for%20Target%20Driven%20Visual%20Navigation&rft.au=Siriwardhana,%20Shamane&rft.date=2019-08-18&rft_id=info:doi/10.48550/arxiv.1908.06376&rft_dat=%3Carxiv_GOX%3E1908_06376%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |