Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator
In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only de...
Ausführliche Beschreibung
Autor*in: |
Park, Jongcheon [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2022transfer abstract |
---|
Schlagwörter: |
Restored Action Generative Adversarial Imitation Learning |
---|
Umfang: |
7 |
---|
Übergeordnetes Werk: |
Enthalten in: Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal - 2012, the science and engineering of measurement and automation, Amsterdam [u.a.] |
---|---|
Übergeordnetes Werk: |
volume:129 ; year:2022 ; pages:684-690 ; extent:7 |
Links: |
---|
DOI / URN: |
10.1016/j.isatra.2022.02.041 |
---|
Katalog-ID: |
ELV059137495 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV059137495 | ||
003 | DE-627 | ||
005 | 20230626052306.0 | ||
007 | cr uuu---uuuuu | ||
008 | 221103s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.isatra.2022.02.041 |2 doi | |
028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica |
035 | |a (DE-627)ELV059137495 | ||
035 | |a (ELSEVIER)S0019-0578(22)00100-8 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 540 |q VZ |
082 | 0 | 4 | |a 660 |q VZ |
082 | 0 | 4 | |a 540 |q VZ |
084 | |a 35.00 |2 bkl | ||
100 | 1 | |a Park, Jongcheon |e verfasserin |4 aut | |
245 | 1 | 0 | |a Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator |
264 | 1 | |c 2022transfer abstract | |
300 | |a 7 | ||
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a nicht spezifiziert |b z |2 rdamedia | ||
338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
520 | |a In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. | ||
520 | |a In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. | ||
650 | 7 | |a Imitation learning |2 Elsevier | |
650 | 7 | |a Restored Action Generative Adversarial Imitation Learning |2 Elsevier | |
650 | 7 | |a Imitation learning from observation |2 Elsevier | |
650 | 7 | |a Manipulator |2 Elsevier | |
700 | 1 | |a Han, Seungyong |4 oth | |
700 | 1 | |a Lee, S.M. |4 oth | |
773 | 0 | 8 | |i Enthalten in |n Elsevier |t Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal |d 2012 |d the science and engineering of measurement and automation |g Amsterdam [u.a.] |w (DE-627)ELV011067004 |
773 | 1 | 8 | |g volume:129 |g year:2022 |g pages:684-690 |g extent:7 |
856 | 4 | 0 | |u https://doi.org/10.1016/j.isatra.2022.02.041 |3 Volltext |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
912 | |a SSG-OLC-PHA | ||
912 | |a GBV_ILN_22 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_105 | ||
936 | b | k | |a 35.00 |j Chemie: Allgemeines |q VZ |
951 | |a AR | ||
952 | |d 129 |j 2022 |h 684-690 |g 7 |
author_variant |
j p jp |
---|---|
matchkey_str |
parkjongcheonhanseungyongleesm:2022----:etrdcineeaiedesraiiainerigrmbev |
hierarchy_sort_str |
2022transfer abstract |
bklnumber |
35.00 |
publishDate |
2022 |
allfields |
10.1016/j.isatra.2022.02.041 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica (DE-627)ELV059137495 (ELSEVIER)S0019-0578(22)00100-8 DE-627 ger DE-627 rakwb eng 540 VZ 660 VZ 540 VZ 35.00 bkl Park, Jongcheon verfasserin aut Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator 2022transfer abstract 7 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Elsevier Han, Seungyong oth Lee, S.M. oth Enthalten in Elsevier Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal 2012 the science and engineering of measurement and automation Amsterdam [u.a.] (DE-627)ELV011067004 volume:129 year:2022 pages:684-690 extent:7 https://doi.org/10.1016/j.isatra.2022.02.041 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_22 GBV_ILN_40 GBV_ILN_105 35.00 Chemie: Allgemeines VZ AR 129 2022 684-690 7 |
spelling |
10.1016/j.isatra.2022.02.041 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica (DE-627)ELV059137495 (ELSEVIER)S0019-0578(22)00100-8 DE-627 ger DE-627 rakwb eng 540 VZ 660 VZ 540 VZ 35.00 bkl Park, Jongcheon verfasserin aut Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator 2022transfer abstract 7 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Elsevier Han, Seungyong oth Lee, S.M. oth Enthalten in Elsevier Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal 2012 the science and engineering of measurement and automation Amsterdam [u.a.] (DE-627)ELV011067004 volume:129 year:2022 pages:684-690 extent:7 https://doi.org/10.1016/j.isatra.2022.02.041 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_22 GBV_ILN_40 GBV_ILN_105 35.00 Chemie: Allgemeines VZ AR 129 2022 684-690 7 |
allfields_unstemmed |
10.1016/j.isatra.2022.02.041 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica (DE-627)ELV059137495 (ELSEVIER)S0019-0578(22)00100-8 DE-627 ger DE-627 rakwb eng 540 VZ 660 VZ 540 VZ 35.00 bkl Park, Jongcheon verfasserin aut Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator 2022transfer abstract 7 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Elsevier Han, Seungyong oth Lee, S.M. oth Enthalten in Elsevier Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal 2012 the science and engineering of measurement and automation Amsterdam [u.a.] (DE-627)ELV011067004 volume:129 year:2022 pages:684-690 extent:7 https://doi.org/10.1016/j.isatra.2022.02.041 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_22 GBV_ILN_40 GBV_ILN_105 35.00 Chemie: Allgemeines VZ AR 129 2022 684-690 7 |
allfieldsGer |
10.1016/j.isatra.2022.02.041 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica (DE-627)ELV059137495 (ELSEVIER)S0019-0578(22)00100-8 DE-627 ger DE-627 rakwb eng 540 VZ 660 VZ 540 VZ 35.00 bkl Park, Jongcheon verfasserin aut Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator 2022transfer abstract 7 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Elsevier Han, Seungyong oth Lee, S.M. oth Enthalten in Elsevier Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal 2012 the science and engineering of measurement and automation Amsterdam [u.a.] (DE-627)ELV011067004 volume:129 year:2022 pages:684-690 extent:7 https://doi.org/10.1016/j.isatra.2022.02.041 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_22 GBV_ILN_40 GBV_ILN_105 35.00 Chemie: Allgemeines VZ AR 129 2022 684-690 7 |
allfieldsSound |
10.1016/j.isatra.2022.02.041 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica (DE-627)ELV059137495 (ELSEVIER)S0019-0578(22)00100-8 DE-627 ger DE-627 rakwb eng 540 VZ 660 VZ 540 VZ 35.00 bkl Park, Jongcheon verfasserin aut Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator 2022transfer abstract 7 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Elsevier Han, Seungyong oth Lee, S.M. oth Enthalten in Elsevier Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal 2012 the science and engineering of measurement and automation Amsterdam [u.a.] (DE-627)ELV011067004 volume:129 year:2022 pages:684-690 extent:7 https://doi.org/10.1016/j.isatra.2022.02.041 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_22 GBV_ILN_40 GBV_ILN_105 35.00 Chemie: Allgemeines VZ AR 129 2022 684-690 7 |
language |
English |
source |
Enthalten in Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal Amsterdam [u.a.] volume:129 year:2022 pages:684-690 extent:7 |
sourceStr |
Enthalten in Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal Amsterdam [u.a.] volume:129 year:2022 pages:684-690 extent:7 |
format_phy_str_mv |
Article |
bklname |
Chemie: Allgemeines |
institution |
findex.gbv.de |
topic_facet |
Imitation learning Restored Action Generative Adversarial Imitation Learning Imitation learning from observation Manipulator |
dewey-raw |
540 |
isfreeaccess_bool |
false |
container_title |
Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal |
authorswithroles_txt_mv |
Park, Jongcheon @@aut@@ Han, Seungyong @@oth@@ Lee, S.M. @@oth@@ |
publishDateDaySort_date |
2022-01-01T00:00:00Z |
hierarchy_top_id |
ELV011067004 |
dewey-sort |
3540 |
id |
ELV059137495 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV059137495</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626052306.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221103s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.isatra.2022.02.041</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV059137495</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0019-0578(22)00100-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">540</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">540</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">35.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Park, Jongcheon</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">7</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Imitation learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Restored Action Generative Adversarial Imitation Learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Imitation learning from observation</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Manipulator</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, Seungyong</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, S.M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="t">Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal</subfield><subfield code="d">2012</subfield><subfield code="d">the science and engineering of measurement and automation</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV011067004</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:129</subfield><subfield code="g">year:2022</subfield><subfield code="g">pages:684-690</subfield><subfield code="g">extent:7</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.isatra.2022.02.041</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">35.00</subfield><subfield code="j">Chemie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">129</subfield><subfield code="j">2022</subfield><subfield code="h">684-690</subfield><subfield code="g">7</subfield></datafield></record></collection>
|
author |
Park, Jongcheon |
spellingShingle |
Park, Jongcheon ddc 540 ddc 660 bkl 35.00 Elsevier Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator |
authorStr |
Park, Jongcheon |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV011067004 |
format |
electronic Article |
dewey-ones |
540 - Chemistry & allied sciences 660 - Chemical engineering |
delete_txt_mv |
keep |
author_role |
aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
540 VZ 660 VZ 35.00 bkl Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator Elsevier |
topic |
ddc 540 ddc 660 bkl 35.00 Elsevier Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator |
topic_unstemmed |
ddc 540 ddc 660 bkl 35.00 Elsevier Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator |
topic_browse |
ddc 540 ddc 660 bkl 35.00 Elsevier Imitation learning Elsevier Restored Action Generative Adversarial Imitation Learning Elsevier Imitation learning from observation Elsevier Manipulator |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
zu |
author2_variant |
s h sh s l sl |
hierarchy_parent_title |
Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal |
hierarchy_parent_id |
ELV011067004 |
dewey-tens |
540 - Chemistry 660 - Chemical engineering |
hierarchy_top_title |
Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)ELV011067004 |
title |
Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator |
ctrlnum |
(DE-627)ELV059137495 (ELSEVIER)S0019-0578(22)00100-8 |
title_full |
Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator |
author_sort |
Park, Jongcheon |
journal |
Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal |
journalStr |
Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
500 - Science 600 - Technology |
recordtype |
marc |
publishDateSort |
2022 |
contenttype_str_mv |
zzz |
container_start_page |
684 |
author_browse |
Park, Jongcheon |
container_volume |
129 |
physical |
7 |
class |
540 VZ 660 VZ 35.00 bkl |
format_se |
Elektronische Aufsätze |
author-letter |
Park, Jongcheon |
doi_str_mv |
10.1016/j.isatra.2022.02.041 |
dewey-full |
540 660 |
title_sort |
restored action generative adversarial imitation learning from observation for robot manipulator |
title_auth |
Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator |
abstract |
In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. |
abstractGer |
In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. |
abstract_unstemmed |
In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_22 GBV_ILN_40 GBV_ILN_105 |
title_short |
Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator |
url |
https://doi.org/10.1016/j.isatra.2022.02.041 |
remote_bool |
true |
author2 |
Han, Seungyong Lee, S.M. |
author2Str |
Han, Seungyong Lee, S.M. |
ppnlink |
ELV011067004 |
mediatype_str_mv |
z |
isOA_txt |
false |
hochschulschrift_bool |
false |
author2_role |
oth oth |
doi_str |
10.1016/j.isatra.2022.02.041 |
up_date |
2024-07-06T21:05:06.628Z |
_version_ |
1803865194893410304 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV059137495</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626052306.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221103s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.isatra.2022.02.041</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001923.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV059137495</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0019-0578(22)00100-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">540</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">540</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">35.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Park, Jongcheon</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">7</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Imitation learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Restored Action Generative Adversarial Imitation Learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Imitation learning from observation</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Manipulator</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, Seungyong</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lee, S.M.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="t">Selective extraction, structural characterisation and antifungal activity assessment of napins from an industrial rapeseed meal</subfield><subfield code="d">2012</subfield><subfield code="d">the science and engineering of measurement and automation</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV011067004</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:129</subfield><subfield code="g">year:2022</subfield><subfield code="g">pages:684-690</subfield><subfield code="g">extent:7</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.isatra.2022.02.041</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">35.00</subfield><subfield code="j">Chemie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">129</subfield><subfield code="j">2022</subfield><subfield code="h">684-690</subfield><subfield code="g">7</subfield></datafield></record></collection>
|
score |
7.3976994 |