Deep Reinforcement Learning: A Brief Survey

Name: Work Video:
Duration: 3 min 30 s
Kai Arulkumaran; Marc Peter Deisenroth; Miles Brundage; Anil A. Bharath
{'id': 'https://openalex.org/W3100789280', 'doi': 'https://doi.org/10.1109/msp.2017.2743240', 'title': 'Deep Reinforcement Learning: A Brief Survey', 'display_name': 'Deep Reinforcement Learning: A Brief Survey', 'publication_year': 2017, 'publication_date': '2017-11-01', 'ids': {'openalex': 'https://openalex.org/W3100789280', 'doi': 'https://doi.org/10.1109/msp.2017.2743240', 'mag': '3100789280'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/msp.2017.2743240', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S120977877', 'display_name': 'IEEE Signal Processing Magazine', 'issn_l': '1053-5888', 'issn': ['1053-5888', '1558-0792'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310319808', 'host_organization_name': 'Institute of Electrical and Electronics Engineers', 'host_organization_lineage': ['https://openalex.org/P4310319808'], 'host_organization_lineage_names': ['Institute of Electrical and Electronics Engineers'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, 'type': 'article', 'type_crossref': 'journal-article', 'indexed_in': ['arxiv', 'crossref', 'datacite'], 'open_access': {'is_oa': True, 'oa_status': 'green', 'oa_url': 'http://arxiv.org/pdf/1708.05866', 'any_repository_has_fulltext': True}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5065210301', 'display_name': 'Kai Arulkumaran', 'orcid': 'https://orcid.org/0000-0003-0459-892X'}, 'institutions': [], 'countries': [], 'is_corresponding': False, 'raw_author_name': 'Kai Arulkumaran', 'raw_affiliation_strings': ['Department of Bioengineering'], 'affiliations': [{'raw_affiliation_string': 'Department of Bioengineering', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5001763022', 'display_name': 'Marc Peter Deisenroth', 'orcid': 'https://orcid.org/0000-0003-1503-680X'}, 'institutions': [], 'countries': [], 'is_corresponding': False, 'raw_author_name': 'Marc Peter Deisenroth', 'raw_affiliation_strings': ['Department of Computing, PROWLER.io'], 'affiliations': [{'raw_affiliation_string': 'Department of Computing, PROWLER.io', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5066559387', 'display_name': 'Miles Brundage', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I4210136895', 'display_name': 'Institute for the Future', 'ror': 'https://ror.org/049tcsg76', 'country_code': 'US', 'type': 'nonprofit', 'lineage': ['https://openalex.org/I4210136895']}, {'id': 'https://openalex.org/I96048030', 'display_name': 'Humana (United States)', 'ror': 'https://ror.org/04gxnqr83', 'country_code': 'US', 'type': 'company', 'lineage': ['https://openalex.org/I96048030']}, {'id': 'https://openalex.org/I55732556', 'display_name': 'Arizona State University', 'ror': 'https://ror.org/03efmqc40', 'country_code': 'US', 'type': 'education', 'lineage': ['https://openalex.org/I55732556']}], 'countries': ['US'], 'is_corresponding': False, 'raw_author_name': 'Miles Brundage', 'raw_affiliation_strings': ['Human and Social Dimensions of Science and Technology Department, Arizona State University; University of Oxford, Future of Humanity Institute'], 'affiliations': [{'raw_affiliation_string': 'Human and Social Dimensions of Science and Technology Department, Arizona State University; University of Oxford, Future of Humanity Institute', 'institution_ids': ['https://openalex.org/I4210136895', 'https://openalex.org/I96048030', 'https://openalex.org/I55732556']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5027222571', 'display_name': 'Anil A. Bharath', 'orcid': 'https://orcid.org/0000-0001-8808-2714'}, 'institutions': [{'id': 'https://openalex.org/I4210109553', 'display_name': 'Institution of Engineering and Technology', 'ror': 'https://ror.org/01xqg1464', 'country_code': 'GB', 'type': 'nonprofit', 'lineage': ['https://openalex.org/I4210109553']}, {'id': 'https://openalex.org/I4210162661', 'display_name': 'Cortexica (United Kingdom)', 'ror': 'https://ror.org/03xdnx124', 'country_code': 'GB', 'type': 'company', 'lineage': ['https://openalex.org/I4210162661']}], 'countries': ['GB'], 'is_corresponding': False, 'raw_author_name': 'Anil Anthony Bharath', 'raw_affiliation_strings': ['Cortexica Vision Systems; Institution of Engineering and Technology'], 'affiliations': [{'raw_affiliation_string': 'Cortexica Vision Systems; Institution of Engineering and Technology', 'institution_ids': ['https://openalex.org/I4210109553', 'https://openalex.org/I4210162661']}]}], 'institution_assertions': [], 'countries_distinct_count': 2, 'institutions_distinct_count': 5, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 130.626, 'has_fulltext': True, 'fulltext_origin': 'pdf', 'cited_by_count': 3049, 'citation_normalized_percentile': {'value': 0.999968, 'is_in_top_1_percent': True, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 99, 'max': 100}, 'biblio': {'volume': '34', 'issue': '6', 'first_page': '26', 'last_page': '38'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T10462', 'display_name': 'Reinforcement Learning in Robotics', 'score': 0.9998, 'subfield': {'id': 'https://openalex.org/subfields/1702', 'display_name': 'Artificial Intelligence'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, 'topics': [{'id': 'https://openalex.org/T10462', 'display_name': 'Reinforcement Learning in Robotics', 'score': 0.9998, 'subfield': {'id': 'https://openalex.org/subfields/1702', 'display_name': 'Artificial Intelligence'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, {'id': 'https://openalex.org/T11714', 'display_name': 'Multimodal Machine Learning Applications', 'score': 0.9932, 'subfield': {'id': 'https://openalex.org/subfields/1707', 'display_name': 'Computer Vision and Pattern Recognition'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, {'id': 'https://openalex.org/T11605', 'display_name': 'Visual Attention and Saliency Detection', 'score': 0.989, 'subfield': {'id': 'https://openalex.org/subfields/1707', 'display_name': 'Computer Vision and Pattern Recognition'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}], 'keywords': [], 'concepts': [{'id': 'https://openalex.org/C97541855', 'wikidata': 'https://www.wikidata.org/wiki/Q830687', 'display_name': 'Reinforcement learning', 'level': 2, 'score': 0.934282}, {'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.7229866}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.71706915}, {'id': 'https://openalex.org/C108583219', 'wikidata': 'https://www.wikidata.org/wiki/Q197536', 'display_name': 'Deep learning', 'level': 2, 'score': 0.6893105}, {'id': 'https://openalex.org/C9652623', 'wikidata': 'https://www.wikidata.org/wiki/Q190109', 'display_name': 'Field (mathematics)', 'level': 2, 'score': 0.50110054}, {'id': 'https://openalex.org/C50644808', 'wikidata': 'https://www.wikidata.org/wiki/Q192776', 'display_name': 'Artificial neural network', 'level': 2, 'score': 0.43664715}, {'id': 'https://openalex.org/C34413123', 'wikidata': 'https://www.wikidata.org/wiki/Q170978', 'display_name': 'Robotics', 'level': 3, 'score': 0.42770177}, {'id': 'https://openalex.org/C151319957', 'wikidata': 'https://www.wikidata.org/wiki/Q752739', 'display_name': 'Asynchronous communication', 'level': 2, 'score': 0.41639405}, {'id': 'https://openalex.org/C119857082', 'wikidata': 'https://www.wikidata.org/wiki/Q2539', 'display_name': 'Machine learning', 'level': 1, 'score': 0.39761263}, {'id': 'https://openalex.org/C90509273', 'wikidata': 'https://www.wikidata.org/wiki/Q11012', 'display_name': 'Robot', 'level': 2, 'score': 0.35564113}, {'id': 'https://openalex.org/C76155785', 'wikidata': 'https://www.wikidata.org/wiki/Q418', 'display_name': 'Telecommunications', 'level': 1, 'score': 0.06471494}, {'id': 'https://openalex.org/C33923547', 'wikidata': 'https://www.wikidata.org/wiki/Q395', 'display_name': 'Mathematics', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C202444582', 'wikidata': 'https://www.wikidata.org/wiki/Q837863', 'display_name': 'Pure mathematics', 'level': 1, 'score': 0.0}], 'mesh': [], 'locations_count': 6, 'locations': [{'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/msp.2017.2743240', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S120977877', 'display_name': 'IEEE Signal Processing Magazine', 'issn_l': '1053-5888', 'issn': ['1053-5888', '1558-0792'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310319808', 'host_organization_name': 'Institute of Electrical and Electronics Engineers', 'host_organization_lineage': ['https://openalex.org/P4310319808'], 'host_organization_lineage_names': ['Institute of Electrical and Electronics Engineers'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, {'is_oa': True, 'landing_page_url': 'http://arxiv.org/abs/1708.05866', 'pdf_url': 'http://arxiv.org/pdf/1708.05866', 'source': {'id': 'https://openalex.org/S4306400194', 'display_name': 'arXiv (Cornell University)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I205783295', 'host_organization_name': 'Cornell University', 'host_organization_lineage': ['https://openalex.org/I205783295'], 'host_organization_lineage_names': ['Cornell University'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'submittedVersion', 'is_accepted': False, 'is_published': False}, {'is_oa': True, 'landing_page_url': 'https://arxiv.org/abs/1708.05866', 'pdf_url': 'https://arxiv.org/pdf/1708.05866', 'source': {'id': 'https://openalex.org/S4306400194', 'display_name': 'arXiv (Cornell University)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I205783295', 'host_organization_name': 'Cornell University', 'host_organization_lineage': ['https://openalex.org/I205783295'], 'host_organization_lineage_names': ['Cornell University'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'submittedVersion', 'is_accepted': False, 'is_published': False}, {'is_oa': True, 'landing_page_url': 'https://discovery.ucl.ac.uk/id/eprint/10083557/', 'pdf_url': 'https://discovery.ucl.ac.uk/10083557/1/1708.05866v2.pdf', 'source': {'id': 'https://openalex.org/S4306400024', 'display_name': 'UCL Discovery (University College London)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I45129253', 'host_organization_name': 'University College London', 'host_organization_lineage': ['https://openalex.org/I45129253'], 'host_organization_lineage_names': ['University College London'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'submittedVersion', 'is_accepted': False, 'is_published': False}, {'is_oa': True, 'landing_page_url': 'https://discovery.ucl.ac.uk/id/eprint/10083557/1/1708.05866v2.pdf', 'pdf_url': 'https://discovery.ucl.ac.uk/id/eprint/10083557/1/1708.05866v2.pdf', 'source': {'id': 'https://openalex.org/S4306400024', 'display_name': 'UCL Discovery (University College London)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I45129253', 'host_organization_name': 'University College London', 'host_organization_lineage': ['https://openalex.org/I45129253'], 'host_organization_lineage_names': ['University College London'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'submittedVersion', 'is_accepted': False, 'is_published': False}, {'is_oa': False, 'landing_page_url': 'https://api.datacite.org/dois/10.48550/arxiv.1708.05866', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4393179698', 'display_name': 'DataCite API', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I4210145204', 'host_organization_name': 'DataCite', 'host_organization_lineage': ['https://openalex.org/I4210145204'], 'host_organization_lineage_names': ['DataCite'], 'type': 'metadata'}, 'license': None, 'license_id': None, 'version': None}], 'best_oa_location': {'is_oa': True, 'landing_page_url': 'http://arxiv.org/abs/1708.05866', 'pdf_url': 'http://arxiv.org/pdf/1708.05866', 'source': {'id': 'https://openalex.org/S4306400194', 'display_name': 'arXiv (Cornell University)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I205783295', 'host_organization_name': 'Cornell University', 'host_organization_lineage': ['https://openalex.org/I205783295'], 'host_organization_lineage_names': ['Cornell University'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'submittedVersion', 'is_accepted': False, 'is_published': False}, 'sustainable_development_goals': [{'display_name': 'Partnerships for the goals', 'score': 0.43, 'id': 'https://metadata.un.org/sdg/17'}], 'grants': [], 'datasets': [], 'versions': ['https://openalex.org/W3100789280'], 'referenced_works_count': 199, 'referenced_works': ['https://openalex.org/W1191599655', 'https://openalex.org/W1480527676', 'https://openalex.org/W1490862430', 'https://openalex.org/W1498436455', 'https://openalex.org/W1499669280', 'https://openalex.org/W1514535095', 'https://openalex.org/W1564755532', 'https://openalex.org/W1573503290', 'https://openalex.org/W1600437712', 'https://openalex.org/W1646152356', 'https://openalex.org/W1658008008', 'https://openalex.org/W166862392', 'https://openalex.org/W1681299129', 'https://openalex.org/W172298727', 'https://openalex.org/W1771410628', 'https://openalex.org/W1821462560', 'https://openalex.org/W1870822514', 'https://openalex.org/W1909320841', 'https://openalex.org/W1929981607', 'https://openalex.org/W1931877416', 'https://openalex.org/W1949804828', 'https://openalex.org/W1957496711', 'https://openalex.org/W1959608418', 'https://openalex.org/W1968962398', 'https://openalex.org/W1987150989', 'https://openalex.org/W2002196558', 'https://openalex.org/W2009303086', 'https://openalex.org/W2009551863', 'https://openalex.org/W2012587148', 'https://openalex.org/W2026659355', 'https://openalex.org/W2027968610', 'https://openalex.org/W2038794597', 'https://openalex.org/W2046765929', 'https://openalex.org/W2056354534', 'https://openalex.org/W2056653303', 'https://openalex.org/W2061562262', 'https://openalex.org/W2091565802', 'https://openalex.org/W2099471712', 'https://openalex.org/W2099618002', 'https://openalex.org/W2103581399', 'https://openalex.org/W2104733512', 'https://openalex.org/W2109910161', 'https://openalex.org/W2115211925', 'https://openalex.org/W2116001481', 'https://openalex.org/W2118688707', 'https://openalex.org/W2119717200', 'https://openalex.org/W2121092017', 'https://openalex.org/W2121103318', 'https://openalex.org/W2121863487', 'https://openalex.org/W2129670787', 'https://openalex.org/W2130801532', 'https://openalex.org/W2131600418', 'https://openalex.org/W2137376508', 'https://openalex.org/W2138243089', 'https://openalex.org/W2139053308', 'https://openalex.org/W2139418546', 'https://openalex.org/W2141559645', 'https://openalex.org/W2145339207', 'https://openalex.org/W2155007355', 'https://openalex.org/W2155968351', 'https://openalex.org/W2156737235', 'https://openalex.org/W2158782408', 'https://openalex.org/W2163922914', 'https://openalex.org/W2165150801', 'https://openalex.org/W2167224731', 'https://openalex.org/W2168231600', 'https://openalex.org/W2168359464', 'https://openalex.org/W2171278097', 'https://openalex.org/W2173564293', 'https://openalex.org/W2174364281', 'https://openalex.org/W2176263492', 'https://openalex.org/W2192203593', 'https://openalex.org/W2195446438', 'https://openalex.org/W2201581102', 'https://openalex.org/W2257979135', 'https://openalex.org/W2280163991', 'https://openalex.org/W2290354866', 'https://openalex.org/W2291973609', 'https://openalex.org/W2342662072', 'https://openalex.org/W2344023930', 'https://openalex.org/W2344556769', 'https://openalex.org/W2395575420', 'https://openalex.org/W2417089653', 'https://openalex.org/W2417786368', 'https://openalex.org/W2442341664', 'https://openalex.org/W2480004914', 'https://openalex.org/W2510924756', 'https://openalex.org/W2518713116', 'https://openalex.org/W2521274174', 'https://openalex.org/W2530944449', 'https://openalex.org/W2547416798', 'https://openalex.org/W2551887912', 'https://openalex.org/W2553303224', 'https://openalex.org/W2553347458', 'https://openalex.org/W2554984891', 'https://openalex.org/W2560678327', 'https://openalex.org/W2567015638', 'https://openalex.org/W2578206533', 'https://openalex.org/W2580175322', 'https://openalex.org/W2591957724', 'https://openalex.org/W2593044849', 'https://openalex.org/W2594794854', 'https://openalex.org/W2594829461', 'https://openalex.org/W2596367596', 'https://openalex.org/W2604283518', 'https://openalex.org/W2606047872', 'https://openalex.org/W2607198029', 'https://openalex.org/W2609650878', 'https://openalex.org/W2612610049', 'https://openalex.org/W2615790994', 'https://openalex.org/W2620671107', 'https://openalex.org/W2624780181', 'https://openalex.org/W2726187156', 'https://openalex.org/W2735995851', 'https://openalex.org/W2736601468', 'https://openalex.org/W2738675347', 'https://openalex.org/W2749807327', 'https://openalex.org/W2751973545', 'https://openalex.org/W2756196406', 'https://openalex.org/W2787259794', 'https://openalex.org/W2911296969', 'https://openalex.org/W2919115771', 'https://openalex.org/W2949267040', 'https://openalex.org/W2949475445', 'https://openalex.org/W2950471160', 'https://openalex.org/W2950560044', 'https://openalex.org/W2950872548', 'https://openalex.org/W2951507724', 'https://openalex.org/W2951527505', 'https://openalex.org/W2951799221', 'https://openalex.org/W2952509347', 'https://openalex.org/W2952523895', 'https://openalex.org/W2952629144', 'https://openalex.org/W2962730405', 'https://openalex.org/W2962736495', 'https://openalex.org/W2962764591', 'https://openalex.org/W2962841471', 'https://openalex.org/W2962872206', 'https://openalex.org/W2962887844', 'https://openalex.org/W2962897886', 'https://openalex.org/W2962938178', 'https://openalex.org/W2962986780', 'https://openalex.org/W2963000099', 'https://openalex.org/W2963038698', 'https://openalex.org/W2963095800', 'https://openalex.org/W2963170229', 'https://openalex.org/W2963184621', 'https://openalex.org/W2963262099', 'https://openalex.org/W2963276097', 'https://openalex.org/W2963277051', 'https://openalex.org/W2963293533', 'https://openalex.org/W2963305465', 'https://openalex.org/W2963430173', 'https://openalex.org/W2963477884', 'https://openalex.org/W2963523627', 'https://openalex.org/W2963634205', 'https://openalex.org/W2963639957', 'https://openalex.org/W2963674921', 'https://openalex.org/W2963830168', 'https://openalex.org/W2963864421', 'https://openalex.org/W2963871073', 'https://openalex.org/W2963938771', 'https://openalex.org/W2963948945', 'https://openalex.org/W2964006217', 'https://openalex.org/W2964043796', 'https://openalex.org/W2964118262', 'https://openalex.org/W2964161785', 'https://openalex.org/W2964164283', 'https://openalex.org/W2964227312', 'https://openalex.org/W2964250653', 'https://openalex.org/W2964338167', 'https://openalex.org/W2964352247', 'https://openalex.org/W3021208093', 'https://openalex.org/W3097999317', 'https://openalex.org/W3103559770', 'https://openalex.org/W3139377883', 'https://openalex.org/W32403112', 'https://openalex.org/W4205513846', 'https://openalex.org/W4214717370', 'https://openalex.org/W4241521318', 'https://openalex.org/W4254755460', 'https://openalex.org/W4293396018', 'https://openalex.org/W4293862243', 'https://openalex.org/W4297732320', 'https://openalex.org/W4297795161', 'https://openalex.org/W4297804343', 'https://openalex.org/W4298174377', 'https://openalex.org/W4298876402', 'https://openalex.org/W4300971732', 'https://openalex.org/W4302570325', 'https://openalex.org/W4319988532', 'https://openalex.org/W4320013936', 'https://openalex.org/W4362203700', 'https://openalex.org/W4394652010', 'https://openalex.org/W4394666657', 'https://openalex.org/W4394672593', 'https://openalex.org/W567721252', 'https://openalex.org/W779494576', 'https://openalex.org/W834081922'], 'related_works': ['https://openalex.org/W4306904969', 'https://openalex.org/W4225981436', 'https://openalex.org/W4207086172', 'https://openalex.org/W2770353918', 'https://openalex.org/W2584231425', 'https://openalex.org/W2156185805', 'https://openalex.org/W2155261584', 'https://openalex.org/W2150611273', 'https://openalex.org/W2116677773', 'https://openalex.org/W2042919702'], 'abstract_inverted_index': {'Deep': [0, 53], 'reinforcement': [1, 33, 54, 91, 112, 142], 'learning': [2, 30, 34, 45, 55], 'is': [3, 31], 'poised': [4], 'to': [5, 35, 37, 46, 60, 67, 86, 95], 'revolutionise': [6], 'the': [7, 25, 75, 87, 96, 115, 130, 154], 'field': [8, 89], 'of': [9, 24, 90, 99, 133, 151], 'AI': [10], 'and': [11, 101, 122], 'represents': [12], 'a': [13, 20], 'step': [14], 'towards': [15], 'building': [16], 'autonomous': [17], 'systems': [18], 'with': [19, 83], 'higher': [21], 'level': [22], 'understanding': [23, 140], 'visual': [26, 139], 'world.': [27, 77], 'Currently,': [28], 'deep': [29, 111, 116, 134], 'enabling': [32], 'scale': [36], 'problems': [38], 'that': [39], 'were': [40], 'previously': [41], 'intractable,': [42], 'such': [43], 'as': [44], 'play': [47], 'video': [48], 'games': [49], 'directly': [50, 70], 'from': [51, 71], 'pixels.': [52], 'algorithms': [56, 109], 'are': [57], 'also': [58], 'applied': [59], 'robotics,': [61], 'allowing': [62], 'control': [63], 'policies': [64], 'for': [65], 'robots': [66], 'be': [68], 'learned': [69], 'camera': [72], 'inputs': [73], 'in': [74, 110], 'real': [76], 'In': [78, 126], 'this': [79], 'survey,': [80], 'we': [81, 128, 146], 'begin': [82], 'an': [84], 'introduction': [85], 'general': [88], 'learning,': [92, 113], 'then': [93], 'progress': [94], 'main': [97], 'streams': [98], 'value-based': [100], 'policy-based': [102], 'methods.': [103], 'Our': [104], 'survey': [105], 'will': [106], 'cover': [107], 'central': [108], 'including': [114], '$Q$-network,': [117], 'trust': [118], 'region': [119], 'policy': [120], 'optimisation,': [121], 'asynchronous': [123], 'advantage': [124], 'actor-critic.': [125], 'parallel,': [127], 'highlight': [129], 'unique': [131], 'advantages': [132], 'neural': [135], 'networks,': [136], 'focusing': [137], 'on': [138], 'via': [141], 'learning.': [143], 'To': [144], 'conclude,': [145], 'describe': [147], 'several': [148], 'current': [149], 'areas': [150], 'research': [152], 'within': [153], 'field.': [155]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W3100789280', 'counts_by_year': [{'year': 2024, 'cited_by_count': 511}, {'year': 2023, 'cited_by_count': 704}, {'year': 2022, 'cited_by_count': 552}, {'year': 2021, 'cited_by_count': 496}, {'year': 2020, 'cited_by_count': 363}, {'year': 2019, 'cited_by_count': 237}, {'year': 2018, 'cited_by_count': 85}, {'year': 2017, 'cited_by_count': 3}], 'updated_date': '2024-12-23T08:38:53.666373', 'created_date': '2020-11-23'}
Publication Information

Basic Information

Access and Citation

AI Researcher Chatbot

Primary Location

Authors

Topics

Keywords

Related Works
