Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis
Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some r...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Zhang, Hengzhe [verfasserIn] Zhou, Aimin [verfasserIn] Lin, Xin [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2020 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Complex & intelligent systems - Berlin : SpringerOpen, 2015, 6(2020), 3 vom: 25. Juli, Seite 741-753 |
|---|---|
| Übergeordnetes Werk: |
volume:6 ; year:2020 ; number:3 ; day:25 ; month:07 ; pages:741-753 |
| Links: |
|---|
| DOI / URN: |
10.1007/s40747-020-00175-y |
|---|
| Katalog-ID: |
SPR040868060 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR040868060 | ||
| 003 | DE-627 | ||
| 005 | 20220112030946.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 201007s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s40747-020-00175-y |2 doi | |
| 035 | |a (DE-627)SPR040868060 | ||
| 035 | |a (SPR)s40747-020-00175-y-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q ASE |
| 100 | 1 | |a Zhang, Hengzhe |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. | ||
| 650 | 4 | |a Reinforcement learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Genetic programming |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Policy derivation |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Explainable machine learning |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Zhou, Aimin |e verfasserin |4 aut | |
| 700 | 1 | |a Lin, Xin |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Complex & intelligent systems |d Berlin : SpringerOpen, 2015 |g 6(2020), 3 vom: 25. Juli, Seite 741-753 |w (DE-627)835589269 |w (DE-600)2834740-7 |x 2198-6053 |7 nnns |
| 773 | 1 | 8 | |g volume:6 |g year:2020 |g number:3 |g day:25 |g month:07 |g pages:741-753 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s40747-020-00175-y |z kostenfrei |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 912 | |a GBV_ILN_11 | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_23 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_31 | ||
| 912 | |a GBV_ILN_39 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_60 | ||
| 912 | |a GBV_ILN_62 | ||
| 912 | |a GBV_ILN_63 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_69 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_95 | ||
| 912 | |a GBV_ILN_105 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_151 | ||
| 912 | |a GBV_ILN_161 | ||
| 912 | |a GBV_ILN_170 | ||
| 912 | |a GBV_ILN_213 | ||
| 912 | |a GBV_ILN_230 | ||
| 912 | |a GBV_ILN_285 | ||
| 912 | |a GBV_ILN_293 | ||
| 912 | |a GBV_ILN_370 | ||
| 912 | |a GBV_ILN_602 | ||
| 912 | |a GBV_ILN_2014 | ||
| 912 | |a GBV_ILN_4012 | ||
| 912 | |a GBV_ILN_4037 | ||
| 912 | |a GBV_ILN_4112 | ||
| 912 | |a GBV_ILN_4125 | ||
| 912 | |a GBV_ILN_4126 | ||
| 912 | |a GBV_ILN_4249 | ||
| 912 | |a GBV_ILN_4305 | ||
| 912 | |a GBV_ILN_4306 | ||
| 912 | |a GBV_ILN_4307 | ||
| 912 | |a GBV_ILN_4313 | ||
| 912 | |a GBV_ILN_4322 | ||
| 912 | |a GBV_ILN_4323 | ||
| 912 | |a GBV_ILN_4324 | ||
| 912 | |a GBV_ILN_4325 | ||
| 912 | |a GBV_ILN_4326 | ||
| 912 | |a GBV_ILN_4335 | ||
| 912 | |a GBV_ILN_4338 | ||
| 912 | |a GBV_ILN_4367 | ||
| 912 | |a GBV_ILN_4700 | ||
| 951 | |a AR | ||
| 952 | |d 6 |j 2020 |e 3 |b 25 |c 07 |h 741-753 | ||
| author_variant |
h z hz a z az x l xl |
|---|---|
| matchkey_str |
article:21986053:2020----::nepealplcdrvtofrenocmnlannbsdnvlt |
| hierarchy_sort_str |
2020 |
| publishDate |
2020 |
| allfields |
10.1007/s40747-020-00175-y doi (DE-627)SPR040868060 (SPR)s40747-020-00175-y-e DE-627 ger DE-627 rakwb eng 004 ASE Zhang, Hengzhe verfasserin aut Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. Reinforcement learning (dpeaa)DE-He213 Genetic programming (dpeaa)DE-He213 Policy derivation (dpeaa)DE-He213 Explainable machine learning (dpeaa)DE-He213 Zhou, Aimin verfasserin aut Lin, Xin verfasserin aut Enthalten in Complex & intelligent systems Berlin : SpringerOpen, 2015 6(2020), 3 vom: 25. Juli, Seite 741-753 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:6 year:2020 number:3 day:25 month:07 pages:741-753 https://dx.doi.org/10.1007/s40747-020-00175-y kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 6 2020 3 25 07 741-753 |
| spelling |
10.1007/s40747-020-00175-y doi (DE-627)SPR040868060 (SPR)s40747-020-00175-y-e DE-627 ger DE-627 rakwb eng 004 ASE Zhang, Hengzhe verfasserin aut Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. Reinforcement learning (dpeaa)DE-He213 Genetic programming (dpeaa)DE-He213 Policy derivation (dpeaa)DE-He213 Explainable machine learning (dpeaa)DE-He213 Zhou, Aimin verfasserin aut Lin, Xin verfasserin aut Enthalten in Complex & intelligent systems Berlin : SpringerOpen, 2015 6(2020), 3 vom: 25. Juli, Seite 741-753 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:6 year:2020 number:3 day:25 month:07 pages:741-753 https://dx.doi.org/10.1007/s40747-020-00175-y kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 6 2020 3 25 07 741-753 |
| allfields_unstemmed |
10.1007/s40747-020-00175-y doi (DE-627)SPR040868060 (SPR)s40747-020-00175-y-e DE-627 ger DE-627 rakwb eng 004 ASE Zhang, Hengzhe verfasserin aut Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. Reinforcement learning (dpeaa)DE-He213 Genetic programming (dpeaa)DE-He213 Policy derivation (dpeaa)DE-He213 Explainable machine learning (dpeaa)DE-He213 Zhou, Aimin verfasserin aut Lin, Xin verfasserin aut Enthalten in Complex & intelligent systems Berlin : SpringerOpen, 2015 6(2020), 3 vom: 25. Juli, Seite 741-753 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:6 year:2020 number:3 day:25 month:07 pages:741-753 https://dx.doi.org/10.1007/s40747-020-00175-y kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 6 2020 3 25 07 741-753 |
| allfieldsGer |
10.1007/s40747-020-00175-y doi (DE-627)SPR040868060 (SPR)s40747-020-00175-y-e DE-627 ger DE-627 rakwb eng 004 ASE Zhang, Hengzhe verfasserin aut Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. Reinforcement learning (dpeaa)DE-He213 Genetic programming (dpeaa)DE-He213 Policy derivation (dpeaa)DE-He213 Explainable machine learning (dpeaa)DE-He213 Zhou, Aimin verfasserin aut Lin, Xin verfasserin aut Enthalten in Complex & intelligent systems Berlin : SpringerOpen, 2015 6(2020), 3 vom: 25. Juli, Seite 741-753 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:6 year:2020 number:3 day:25 month:07 pages:741-753 https://dx.doi.org/10.1007/s40747-020-00175-y kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 6 2020 3 25 07 741-753 |
| allfieldsSound |
10.1007/s40747-020-00175-y doi (DE-627)SPR040868060 (SPR)s40747-020-00175-y-e DE-627 ger DE-627 rakwb eng 004 ASE Zhang, Hengzhe verfasserin aut Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis 2020 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. Reinforcement learning (dpeaa)DE-He213 Genetic programming (dpeaa)DE-He213 Policy derivation (dpeaa)DE-He213 Explainable machine learning (dpeaa)DE-He213 Zhou, Aimin verfasserin aut Lin, Xin verfasserin aut Enthalten in Complex & intelligent systems Berlin : SpringerOpen, 2015 6(2020), 3 vom: 25. Juli, Seite 741-753 (DE-627)835589269 (DE-600)2834740-7 2198-6053 nnns volume:6 year:2020 number:3 day:25 month:07 pages:741-753 https://dx.doi.org/10.1007/s40747-020-00175-y kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 6 2020 3 25 07 741-753 |
| language |
English |
| source |
Enthalten in Complex & intelligent systems 6(2020), 3 vom: 25. Juli, Seite 741-753 volume:6 year:2020 number:3 day:25 month:07 pages:741-753 |
| sourceStr |
Enthalten in Complex & intelligent systems 6(2020), 3 vom: 25. Juli, Seite 741-753 volume:6 year:2020 number:3 day:25 month:07 pages:741-753 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Reinforcement learning Genetic programming Policy derivation Explainable machine learning |
| dewey-raw |
004 |
| isfreeaccess_bool |
true |
| container_title |
Complex & intelligent systems |
| authorswithroles_txt_mv |
Zhang, Hengzhe @@aut@@ Zhou, Aimin @@aut@@ Lin, Xin @@aut@@ |
| publishDateDaySort_date |
2020-07-25T00:00:00Z |
| hierarchy_top_id |
835589269 |
| dewey-sort |
14 |
| id |
SPR040868060 |
| 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">SPR040868060</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220112030946.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">201007s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s40747-020-00175-y</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR040868060</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s40747-020-00175-y-e</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">004</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhang, Hengzhe</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Reinforcement learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Genetic programming</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Policy derivation</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Explainable machine learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhou, Aimin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lin, Xin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Complex & intelligent systems</subfield><subfield code="d">Berlin : SpringerOpen, 2015</subfield><subfield code="g">6(2020), 3 vom: 25. Juli, Seite 741-753</subfield><subfield code="w">(DE-627)835589269</subfield><subfield code="w">(DE-600)2834740-7</subfield><subfield code="x">2198-6053</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:6</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:3</subfield><subfield code="g">day:25</subfield><subfield code="g">month:07</subfield><subfield code="g">pages:741-753</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s40747-020-00175-y</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</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_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</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_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">6</subfield><subfield code="j">2020</subfield><subfield code="e">3</subfield><subfield code="b">25</subfield><subfield code="c">07</subfield><subfield code="h">741-753</subfield></datafield></record></collection>
|
| author |
Zhang, Hengzhe |
| spellingShingle |
Zhang, Hengzhe ddc 004 misc Reinforcement learning misc Genetic programming misc Policy derivation misc Explainable machine learning Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| authorStr |
Zhang, Hengzhe |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)835589269 |
| format |
electronic Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
2198-6053 |
| topic_title |
004 ASE Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis Reinforcement learning (dpeaa)DE-He213 Genetic programming (dpeaa)DE-He213 Policy derivation (dpeaa)DE-He213 Explainable machine learning (dpeaa)DE-He213 |
| topic |
ddc 004 misc Reinforcement learning misc Genetic programming misc Policy derivation misc Explainable machine learning |
| topic_unstemmed |
ddc 004 misc Reinforcement learning misc Genetic programming misc Policy derivation misc Explainable machine learning |
| topic_browse |
ddc 004 misc Reinforcement learning misc Genetic programming misc Policy derivation misc Explainable machine learning |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Complex & intelligent systems |
| hierarchy_parent_id |
835589269 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Complex & intelligent systems |
| isfreeaccess_txt |
true |
| familylinks_str_mv |
(DE-627)835589269 (DE-600)2834740-7 |
| title |
Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| ctrlnum |
(DE-627)SPR040868060 (SPR)s40747-020-00175-y-e |
| title_full |
Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| author_sort |
Zhang, Hengzhe |
| journal |
Complex & intelligent systems |
| journalStr |
Complex & intelligent systems |
| lang_code |
eng |
| isOA_bool |
true |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2020 |
| contenttype_str_mv |
txt |
| container_start_page |
741 |
| author_browse |
Zhang, Hengzhe Zhou, Aimin Lin, Xin |
| container_volume |
6 |
| class |
004 ASE |
| format_se |
Elektronische Aufsätze |
| author-letter |
Zhang, Hengzhe |
| doi_str_mv |
10.1007/s40747-020-00175-y |
| dewey-full |
004 |
| author2-role |
verfasserin |
| title_sort |
interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| title_auth |
Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| abstract |
Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. |
| abstractGer |
Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. |
| abstract_unstemmed |
Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 |
| container_issue |
3 |
| title_short |
Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis |
| url |
https://dx.doi.org/10.1007/s40747-020-00175-y |
| remote_bool |
true |
| author2 |
Zhou, Aimin Lin, Xin |
| author2Str |
Zhou, Aimin Lin, Xin |
| ppnlink |
835589269 |
| mediatype_str_mv |
c |
| isOA_txt |
true |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s40747-020-00175-y |
| up_date |
2024-07-03T18:46:36.559Z |
| _version_ |
1803584690255298560 |
| 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">SPR040868060</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220112030946.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">201007s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s40747-020-00175-y</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR040868060</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s40747-020-00175-y-e</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">004</subfield><subfield code="q">ASE</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhang, Hengzhe</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Reinforcement learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Genetic programming</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Policy derivation</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Explainable machine learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhou, Aimin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lin, Xin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Complex & intelligent systems</subfield><subfield code="d">Berlin : SpringerOpen, 2015</subfield><subfield code="g">6(2020), 3 vom: 25. Juli, Seite 741-753</subfield><subfield code="w">(DE-627)835589269</subfield><subfield code="w">(DE-600)2834740-7</subfield><subfield code="x">2198-6053</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:6</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:3</subfield><subfield code="g">day:25</subfield><subfield code="g">month:07</subfield><subfield code="g">pages:741-753</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s40747-020-00175-y</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</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_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</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_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">6</subfield><subfield code="j">2020</subfield><subfield code="e">3</subfield><subfield code="b">25</subfield><subfield code="c">07</subfield><subfield code="h">741-753</subfield></datafield></record></collection>
|
| score |
7.401144 |