Imitation Learning

Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions. Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Hussein, Ahmed [verfasserIn] Gaber, Mohamed Elyan, Eyad Jayne, Chrisina

Format:	Artikel
Sprache:	Englisch

Erschienen:	2017

Schlagwörter:	feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning

Systematik:	SA 2943

Übergeordnetes Werk:	Enthalten in: ACM computing surveys - New York, NY : ACM Press, 1971, 50(2017), 2, Seite 1-35
Übergeordnetes Werk:	volume:50 ; year:2017 ; number:2 ; pages:1-35

Links:	Volltext Link aufrufen

DOI / URN:	10.1145/3054912

Katalog-ID:	OLC1991968000

Internformat


LEADER	01000caa a2200265 4500
001	OLC1991968000
003	DE-627
005	20230715035852.0
007	tu
008	170512s2017 xx \|\|\|\|\| 00\| \|\|eng c
024	7		\|a 10.1145/3054912 \|2 doi
028	5	2	\|a PQ20170721
035			\|a (DE-627)OLC1991968000
035			\|a (DE-599)GBVOLC1991968000
035			\|a (PRQ)acm_primary_30549120
035			\|a (KEY)0016644820170000050000200001imitationlearning
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
082	0	4	\|a 004 \|q DE-600
084			\|a SA 2943 \|q AVZ \|2 rvk
100	1		\|a Hussein, Ahmed \|e verfasserin \|4 aut
245	1	0	\|a Imitation Learning
264		1	\|c 2017
336			\|a Text \|b txt \|2 rdacontent
337			\|a ohne Hilfsmittel zu benutzen \|b n \|2 rdamedia
338			\|a Band \|b nc \|2 rdacarrier
520			\|a Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.
650		4	\|a feature representations
650		4	\|a Imitation learning
650		4	\|a learning from experience
650		4	\|a self-improvement
650		4	\|a learning from demonstrations
650		4	\|a robotics
650		4	\|a intelligent agents
650		4	\|a reinforcement learning
650		4	\|a deep learning
700	1		\|a Gaber, Mohamed \|4 oth
700	1		\|a Elyan, Eyad \|4 oth
700	1		\|a Jayne, Chrisina \|4 oth
773	0	8	\|i Enthalten in \|t ACM computing surveys \|d New York, NY : ACM Press, 1971 \|g 50(2017), 2, Seite 1-35 \|w (DE-627)130416312 \|w (DE-600)626472-4 \|w (DE-576)01824579X \|x 0360-0300 \|7 nnns
773	1	8	\|g volume:50 \|g year:2017 \|g number:2 \|g pages:1-35
856	4	1	\|u http://dx.doi.org/10.1145/3054912 \|3 Volltext
856	4	2	\|u http://dl.acm.org/citation.cfm?id=3054912
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_OLC
912			\|a SSG-OLC-MAT
912			\|a GBV_ILN_24
912			\|a GBV_ILN_30
912			\|a GBV_ILN_70
912			\|a GBV_ILN_2004
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4318
912			\|a GBV_ILN_4336
936	r	v	\|a SA 2943
951			\|a AR
952			\|d 50 \|j 2017 \|e 2 \|h 1-35

Indexfelder

author_variant	a h ah
matchkey_str	article:03600300:2017----::mttola
hierarchy_sort_str	2017
publishDate	2017
allfields	10.1145/3054912 doi PQ20170721 (DE-627)OLC1991968000 (DE-599)GBVOLC1991968000 (PRQ)acm_primary_30549120 (KEY)0016644820170000050000200001imitationlearning DE-627 ger DE-627 rakwb eng 004 DE-600 SA 2943 AVZ rvk Hussein, Ahmed verfasserin aut Imitation Learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions. feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning Gaber, Mohamed oth Elyan, Eyad oth Jayne, Chrisina oth Enthalten in ACM computing surveys New York, NY : ACM Press, 1971 50(2017), 2, Seite 1-35 (DE-627)130416312 (DE-600)626472-4 (DE-576)01824579X 0360-0300 nnns volume:50 year:2017 number:2 pages:1-35 http://dx.doi.org/10.1145/3054912 Volltext http://dl.acm.org/citation.cfm?id=3054912 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_30 GBV_ILN_70 GBV_ILN_2004 GBV_ILN_4125 GBV_ILN_4318 GBV_ILN_4336 SA 2943 AR 50 2017 2 1-35
spelling	10.1145/3054912 doi PQ20170721 (DE-627)OLC1991968000 (DE-599)GBVOLC1991968000 (PRQ)acm_primary_30549120 (KEY)0016644820170000050000200001imitationlearning DE-627 ger DE-627 rakwb eng 004 DE-600 SA 2943 AVZ rvk Hussein, Ahmed verfasserin aut Imitation Learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions. feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning Gaber, Mohamed oth Elyan, Eyad oth Jayne, Chrisina oth Enthalten in ACM computing surveys New York, NY : ACM Press, 1971 50(2017), 2, Seite 1-35 (DE-627)130416312 (DE-600)626472-4 (DE-576)01824579X 0360-0300 nnns volume:50 year:2017 number:2 pages:1-35 http://dx.doi.org/10.1145/3054912 Volltext http://dl.acm.org/citation.cfm?id=3054912 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_30 GBV_ILN_70 GBV_ILN_2004 GBV_ILN_4125 GBV_ILN_4318 GBV_ILN_4336 SA 2943 AR 50 2017 2 1-35
allfields_unstemmed	10.1145/3054912 doi PQ20170721 (DE-627)OLC1991968000 (DE-599)GBVOLC1991968000 (PRQ)acm_primary_30549120 (KEY)0016644820170000050000200001imitationlearning DE-627 ger DE-627 rakwb eng 004 DE-600 SA 2943 AVZ rvk Hussein, Ahmed verfasserin aut Imitation Learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions. feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning Gaber, Mohamed oth Elyan, Eyad oth Jayne, Chrisina oth Enthalten in ACM computing surveys New York, NY : ACM Press, 1971 50(2017), 2, Seite 1-35 (DE-627)130416312 (DE-600)626472-4 (DE-576)01824579X 0360-0300 nnns volume:50 year:2017 number:2 pages:1-35 http://dx.doi.org/10.1145/3054912 Volltext http://dl.acm.org/citation.cfm?id=3054912 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_30 GBV_ILN_70 GBV_ILN_2004 GBV_ILN_4125 GBV_ILN_4318 GBV_ILN_4336 SA 2943 AR 50 2017 2 1-35
allfieldsGer	10.1145/3054912 doi PQ20170721 (DE-627)OLC1991968000 (DE-599)GBVOLC1991968000 (PRQ)acm_primary_30549120 (KEY)0016644820170000050000200001imitationlearning DE-627 ger DE-627 rakwb eng 004 DE-600 SA 2943 AVZ rvk Hussein, Ahmed verfasserin aut Imitation Learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions. feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning Gaber, Mohamed oth Elyan, Eyad oth Jayne, Chrisina oth Enthalten in ACM computing surveys New York, NY : ACM Press, 1971 50(2017), 2, Seite 1-35 (DE-627)130416312 (DE-600)626472-4 (DE-576)01824579X 0360-0300 nnns volume:50 year:2017 number:2 pages:1-35 http://dx.doi.org/10.1145/3054912 Volltext http://dl.acm.org/citation.cfm?id=3054912 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_30 GBV_ILN_70 GBV_ILN_2004 GBV_ILN_4125 GBV_ILN_4318 GBV_ILN_4336 SA 2943 AR 50 2017 2 1-35
allfieldsSound	10.1145/3054912 doi PQ20170721 (DE-627)OLC1991968000 (DE-599)GBVOLC1991968000 (PRQ)acm_primary_30549120 (KEY)0016644820170000050000200001imitationlearning DE-627 ger DE-627 rakwb eng 004 DE-600 SA 2943 AVZ rvk Hussein, Ahmed verfasserin aut Imitation Learning 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions. feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning Gaber, Mohamed oth Elyan, Eyad oth Jayne, Chrisina oth Enthalten in ACM computing surveys New York, NY : ACM Press, 1971 50(2017), 2, Seite 1-35 (DE-627)130416312 (DE-600)626472-4 (DE-576)01824579X 0360-0300 nnns volume:50 year:2017 number:2 pages:1-35 http://dx.doi.org/10.1145/3054912 Volltext http://dl.acm.org/citation.cfm?id=3054912 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_30 GBV_ILN_70 GBV_ILN_2004 GBV_ILN_4125 GBV_ILN_4318 GBV_ILN_4336 SA 2943 AR 50 2017 2 1-35
language	English
source	Enthalten in ACM computing surveys 50(2017), 2, Seite 1-35 volume:50 year:2017 number:2 pages:1-35
sourceStr	Enthalten in ACM computing surveys 50(2017), 2, Seite 1-35 volume:50 year:2017 number:2 pages:1-35
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning
dewey-raw	004
isfreeaccess_bool	false
container_title	ACM computing surveys
authorswithroles_txt_mv	Hussein, Ahmed @@aut@@ Gaber, Mohamed @@oth@@ Elyan, Eyad @@oth@@ Jayne, Chrisina @@oth@@
publishDateDaySort_date	2017-01-01T00:00:00Z
hierarchy_top_id	130416312
dewey-sort	14
id	OLC1991968000
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1991968000</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230715035852.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">170512s2017 xx \|\|\|\|\| 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1145/3054912</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20170721</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1991968000</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1991968000</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)acm_primary_30549120</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0016644820170000050000200001imitationlearning</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">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">SA 2943</subfield><subfield code="q">AVZ</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Hussein, Ahmed</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Imitation Learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</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">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature representations</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Imitation learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">learning from experience</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">self-improvement</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">learning from demonstrations</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">intelligent agents</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">reinforcement learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gaber, Mohamed</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Elyan, Eyad</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Jayne, Chrisina</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">ACM computing surveys</subfield><subfield code="d">New York, NY : ACM Press, 1971</subfield><subfield code="g">50(2017), 2, Seite 1-35</subfield><subfield code="w">(DE-627)130416312</subfield><subfield code="w">(DE-600)626472-4</subfield><subfield code="w">(DE-576)01824579X</subfield><subfield code="x">0360-0300</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:50</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:2</subfield><subfield code="g">pages:1-35</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1145/3054912</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://dl.acm.org/citation.cfm?id=3054912</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_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</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_30</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_2004</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_4318</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4336</subfield></datafield><datafield tag="936" ind1="r" ind2="v"><subfield code="a">SA 2943</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">50</subfield><subfield code="j">2017</subfield><subfield code="e">2</subfield><subfield code="h">1-35</subfield></datafield></record></collection>
author	Hussein, Ahmed
spellingShingle	Hussein, Ahmed ddc 004 rvk SA 2943 misc feature representations misc Imitation learning misc learning from experience misc self-improvement misc learning from demonstrations misc robotics misc intelligent agents misc reinforcement learning misc deep learning Imitation Learning
authorStr	Hussein, Ahmed
ppnlink_with_tag_str_mv	@@773@@(DE-627)130416312
format	Article
dewey-ones	004 - Data processing & computer science
delete_txt_mv	keep
author_role	aut
collection	OLC
remote_str	false
illustrated	Not Illustrated
issn	0360-0300
topic_title	004 DE-600 SA 2943 AVZ rvk Imitation Learning feature representations Imitation learning learning from experience self-improvement learning from demonstrations robotics intelligent agents reinforcement learning deep learning
topic	ddc 004 rvk SA 2943 misc feature representations misc Imitation learning misc learning from experience misc self-improvement misc learning from demonstrations misc robotics misc intelligent agents misc reinforcement learning misc deep learning
topic_unstemmed	ddc 004 rvk SA 2943 misc feature representations misc Imitation learning misc learning from experience misc self-improvement misc learning from demonstrations misc robotics misc intelligent agents misc reinforcement learning misc deep learning
topic_browse	ddc 004 rvk SA 2943 misc feature representations misc Imitation learning misc learning from experience misc self-improvement misc learning from demonstrations misc robotics misc intelligent agents misc reinforcement learning misc deep learning
format_facet	Aufsätze Gedruckte Aufsätze
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	nc
author2_variant	m g mg e e ee c j cj
hierarchy_parent_title	ACM computing surveys
hierarchy_parent_id	130416312
dewey-tens	000 - Computer science, knowledge & systems
hierarchy_top_title	ACM computing surveys
isfreeaccess_txt	false
familylinks_str_mv	(DE-627)130416312 (DE-600)626472-4 (DE-576)01824579X
title	Imitation Learning
ctrlnum	(DE-627)OLC1991968000 (DE-599)GBVOLC1991968000 (PRQ)acm_primary_30549120 (KEY)0016644820170000050000200001imitationlearning
title_full	Imitation Learning
author_sort	Hussein, Ahmed
journal	ACM computing surveys
journalStr	ACM computing surveys
lang_code	eng
isOA_bool	false
dewey-hundreds	000 - Computer science, information & general works
recordtype	marc
publishDateSort	2017
contenttype_str_mv	txt
container_start_page	1
author_browse	Hussein, Ahmed
container_volume	50
class	004 DE-600 SA 2943 AVZ rvk
format_se	Aufsätze
author-letter	Hussein, Ahmed
doi_str_mv	10.1145/3054912
dewey-full	004
title_sort	imitation learning
title_auth	Imitation Learning
abstract	Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.
abstractGer	Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.
abstract_unstemmed	Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_24 GBV_ILN_30 GBV_ILN_70 GBV_ILN_2004 GBV_ILN_4125 GBV_ILN_4318 GBV_ILN_4336
container_issue	2
title_short	Imitation Learning
url	http://dx.doi.org/10.1145/3054912 http://dl.acm.org/citation.cfm?id=3054912
remote_bool	false
author2	Gaber, Mohamed Elyan, Eyad Jayne, Chrisina
author2Str	Gaber, Mohamed Elyan, Eyad Jayne, Chrisina
ppnlink	130416312
mediatype_str_mv	n
isOA_txt	false
hochschulschrift_bool	false
author2_role	oth oth oth
doi_str	10.1145/3054912
up_date	2024-07-04T03:59:49.048Z
_version_	1803619495107887104
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1991968000</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230715035852.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">170512s2017 xx \|\|\|\|\| 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1145/3054912</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20170721</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1991968000</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1991968000</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)acm_primary_30549120</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0016644820170000050000200001imitationlearning</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">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">SA 2943</subfield><subfield code="q">AVZ</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Hussein, Ahmed</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Imitation Learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</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">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature representations</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Imitation learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">learning from experience</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">self-improvement</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">learning from demonstrations</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">intelligent agents</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">reinforcement learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gaber, Mohamed</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Elyan, Eyad</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Jayne, Chrisina</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">ACM computing surveys</subfield><subfield code="d">New York, NY : ACM Press, 1971</subfield><subfield code="g">50(2017), 2, Seite 1-35</subfield><subfield code="w">(DE-627)130416312</subfield><subfield code="w">(DE-600)626472-4</subfield><subfield code="w">(DE-576)01824579X</subfield><subfield code="x">0360-0300</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:50</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:2</subfield><subfield code="g">pages:1-35</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1145/3054912</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://dl.acm.org/citation.cfm?id=3054912</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_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</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_30</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_2004</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_4318</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4336</subfield></datafield><datafield tag="936" ind1="r" ind2="v"><subfield code="a">SA 2943</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">50</subfield><subfield code="j">2017</subfield><subfield code="e">2</subfield><subfield code="h">1-35</subfield></datafield></record></collection>
score	7.400132

Nicht das Richtige dabei?

Schreiben Sie uns!

Imitation Learning

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?