{"id":"https://openalex.org/W2765971296","doi":"https://doi.org/10.1007/978-3-319-69456-6_18","title":"What Does a Policy Network Learn After Mastering a Pong Game?","display_name":"What Does a Policy Network Learn After Mastering a Pong Game?","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2765971296","doi":"https://doi.org/10.1007/978-3-319-69456-6_18","mag":"2765971296"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-69456-6_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-69456-6_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038324843","display_name":"Somnuk Phon-Amnuaisuk","orcid":"https://orcid.org/0000-0003-2130-185X"},"institutions":[{"id":"https://openalex.org/I200859690","display_name":"Universiti Teknologi Brunei","ror":"https://ror.org/004y7f915","country_code":"BN","type":"education","lineage":["https://openalex.org/I200859690"]}],"countries":["BN"],"is_corresponding":true,"raw_author_name":"Somnuk Phon-Amnuaisuk","raw_affiliation_strings":["Media Informatics Special Interest Group, Centre for Innovative Engineering, Universiti Teknologi Brunei, Mukim Gadong, Brunei","School of Computing and Informatics, Universiti Teknologi Brunei, Mukim\u00a0Gadong, Brunei","Universiti Teknologi Brunei, Gadong, Brunei Darussalam"],"affiliations":[{"raw_affiliation_string":"Media Informatics Special Interest Group, Centre for Innovative Engineering, Universiti Teknologi Brunei, Mukim Gadong, Brunei","institution_ids":["https://openalex.org/I200859690"]},{"raw_affiliation_string":"School of Computing and Informatics, Universiti Teknologi Brunei, Mukim\u00a0Gadong, Brunei","institution_ids":["https://openalex.org/I200859690"]},{"raw_affiliation_string":"Universiti Teknologi Brunei, Gadong, Brunei Darussalam","institution_ids":["https://openalex.org/I200859690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5038324843"],"corresponding_institution_ids":["https://openalex.org/I200859690"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16281018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9937999844551086,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9819999933242798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9277462959289551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8270223140716553},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7947198152542114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.630877673625946},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5914962887763977},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5739396214485168},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5322729349136353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4825279414653778},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.41987767815589905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3935418426990509},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3472748398780823}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9277462959289551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270223140716553},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7947198152542114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630877673625946},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5914962887763977},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5739396214485168},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5322729349136353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4825279414653778},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41987767815589905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3935418426990509},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3472748398780823},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-69456-6_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-69456-6_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1785849760","https://openalex.org/W1849277567","https://openalex.org/W1939378489","https://openalex.org/W2041367235","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2163605009","https://openalex.org/W2165150801","https://openalex.org/W2166082022","https://openalex.org/W2257979135","https://openalex.org/W2919115771","https://openalex.org/W2951008357","https://openalex.org/W2963775850","https://openalex.org/W3103780890","https://openalex.org/W4252673275"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W2808418668","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
