{"id":"https://openalex.org/W2184119302","doi":null,"title":"Action Selection and Action Control for Playing Table Soccer Using Markov Decision Processes Master Thesis","display_name":"Action Selection and Action Control for Playing Table Soccer Using Markov Decision Processes Master Thesis","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2184119302","mag":"2184119302"},"language":"en","primary_location":{"id":"mag:2184119302","doi":null,"is_oa":false,"landing_page_url":"http://gki.informatik.uni-freiburg.de/papers/zhang-master-thesis-05.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5002446890","display_name":"Bernhard Nebel","orcid":"https://orcid.org/0000-0002-6833-6323","observed_orcids":["https://orcid.org/0000-0002-6833-6323"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bernhard Nebel","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6833-6323","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5002446890"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0032999999821186066,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00039999998989515007,"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/action-selection","display_name":"action selection","score":0.7900000214576721},{"id":"https://openalex.org/keywords/action-control","display_name":"action control","score":0.968999981880188},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.984000027179718},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9929999709129333},{"id":"https://openalex.org/keywords/policy-iteration","display_name":"policy iteration","score":0.6890000104904175},{"id":"https://openalex.org/keywords/dribbling","display_name":"dribbling","score":0.8500000238418579},{"id":"https://openalex.org/keywords/robot-soccer","display_name":"robot soccer","score":0.6150000095367432},{"id":"https://openalex.org/keywords/state-space-reduction","display_name":"state space reduction","score":0.7329999804496765},{"id":"https://openalex.org/keywords/transition-probabilities","display_name":"transition probabilities","score":0.4490000009536743}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8659944534301758},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6851133108139038},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6765502095222473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6645945310592651},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5450690984725952},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.5437813997268677},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47434937953948975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634753167629242},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4378981590270996},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4278463125228882},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3843972682952881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1453171968460083},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2184119302","doi":null,"is_oa":false,"landing_page_url":"http://gki.informatik.uni-freiburg.de/papers/zhang-master-thesis-05.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1500976337","https://openalex.org/W1507115952","https://openalex.org/W1570101817","https://openalex.org/W1580572138","https://openalex.org/W1980035368","https://openalex.org/W1997477668","https://openalex.org/W2090089645","https://openalex.org/W2107726111","https://openalex.org/W2400168348","https://openalex.org/W2596500414"],"related_works":["https://openalex.org/W7099910749","https://openalex.org/W2347268315","https://openalex.org/W1500976337","https://openalex.org/W2879679159","https://openalex.org/W4235195725","https://openalex.org/W1578481408","https://openalex.org/W2121036955","https://openalex.org/W3095980510","https://openalex.org/W2392618901","https://openalex.org/W3100323192"],"abstract_inverted_index":{"StarKick":[0,21,232],"is":[1,22,31,57,126,147,173],"a":[2,68,77,111,155,195,234],"commercially":[3],"available":[4,16],"table":[5,206],"soccer":[6,207],"robot":[7],"which":[8,105],"challenges":[9],"even":[10],"advanced":[11],"human":[12],"players.":[13],"However,":[14],"the":[15,25,29,41,52,61,64,73,81,85,95,132,135,145,160,176,213,219,225,229,241,246],"set":[17,156],"of":[18,27,43,84,88,157,199,231,239],"actions":[19,30,47,137,143,161,216],"for":[20,35,48],"limited":[23],"and":[24,50,67,101,123,144,159,224],"way":[26],"selecting":[28],"not":[32],"flexible":[33],"enough":[34],"incorporating":[36],"more":[37,141],"elaborate":[38],"actions.":[39],"In":[40,128],"context":[42],"this":[44],"thesis,":[45],"new":[46,93],"stopping":[49],"dribbling":[51],"ball":[53,62,74,96],"are":[54,138,163,182,188,201,217],"developed.":[55,127],"Stopping":[56],"achieved":[58],"by":[59,184,190],"locking":[60],"between":[63],"playing":[65,69,86],"surface":[66],"figure.":[70],"Dribbling":[71],"makes":[72],"rolling":[75],"at":[76],"controllable":[78],"speed":[79],"within":[80],"reachable":[82],"area":[83],"figures":[87],"one":[89],"rod.":[90],"By":[91],"these":[92,166],"actions,":[94],"can":[97],"be":[98,108,253],"deliberately":[99],"passed":[100],"stopped.":[102],"To":[103],"decide,":[104],"action":[106,115],"should":[107],"taken":[109],"in":[110,165,175,204,233,245,255],"given":[112],"situation,":[113],"an":[114],"selection":[116],"scheme":[117],"using":[118],"Markov":[119],"Decision":[120],"Processes":[121],"(MDPs)":[122],"reinforcement":[124,170,226,242],"learning":[125,171,227,243],"order":[129],"to":[130,140,252],"reduce":[131],"state":[133],"space,":[134],"basic":[136],"combined":[139],"complex":[142],"MDP":[146,177,220],"structured":[148],"into":[149],"four":[150],"modules.":[151],"Each":[152],"module":[153],"contains":[154],"states,":[158],"that":[162,212],"applicable":[164],"states.":[167],"A":[168,197],"simple":[169],"algorithm":[172,193],"implemented":[174],"framework.":[178],"The":[179,237],"transition":[180],"probabilities":[181],"updated":[183],"counting.":[185],"These":[186,209],"updates":[187],"spread":[189],"policy":[191],"iteration":[192],"during":[194],"game.":[196,236],"series":[198],"experiments":[200,210],"carried":[202],"out":[203],"real":[205,256],"games.":[208,257],"show":[211],"newly":[214],"developed":[215],"robust,":[218],"model":[221],"works":[222],"fine,":[223],"improves":[228],"performance":[230],"simplified":[235],"attempt":[238],"making":[240],"work":[244],"whole":[247],"game":[248],"seems":[249],"too":[250],"tedious":[251],"finished":[254]},"counts_by_year":[],"updated_date":"2026-07-14T23:32:53.992493","created_date":"2016-06-24T00:00:00"}