{"id":"https://openalex.org/W7204017244","doi":null,"title":"Reasoning-Trace Supervision for Generalisation in FrozenLake Planning","display_name":"Reasoning-Trace Supervision for Generalisation in FrozenLake Planning","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7204017244"},"language":"en","primary_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/147242","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/147242","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/7bdd82ef-5911-4682-b7da-2ce921cc11bd/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G2 Pro gradu, diplomity\u00f6"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://aaltodoc.aalto.fi/bitstreams/7bdd82ef-5911-4682-b7da-2ce921cc11bd/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147826624","display_name":"Chanoknan Tanchotikul","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tanchotikul, Chanoknan","raw_affiliation_strings":["and Information Sciences Major Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"and Information Sciences Major Computer Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147826624"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8661999702453613,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8661999702453613,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.11420000344514847,"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":0.012299999594688416,"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/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.9729999899864197},{"id":"https://openalex.org/keywords/planning","display_name":"planning","score":0.36500000953674316},{"id":"https://openalex.org/keywords/input-representation","display_name":"input representation","score":0.5509999990463257},{"id":"https://openalex.org/keywords/movement-direction","display_name":"movement direction","score":0.5789999961853027},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.515999972820282},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7960000038146973}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6960999965667725},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6690999865531921},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5479000210762024},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/147242","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/147242","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/7bdd82ef-5911-4682-b7da-2ce921cc11bd/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G2 Pro gradu, diplomity\u00f6"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/147242","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/147242","pdf_url":"https://aaltodoc.aalto.fi/bitstreams/7bdd82ef-5911-4682-b7da-2ce921cc11bd/download","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G2 Pro gradu, diplomity\u00f6"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204017244.pdf","grobid_xml":"https://content.openalex.org/works/W7204017244.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1969483458","https://openalex.org/W2789352267","https://openalex.org/W3010805364","https://openalex.org/W3016970897","https://openalex.org/W3030163527","https://openalex.org/W3037207827","https://openalex.org/W3112486745","https://openalex.org/W3215529831","https://openalex.org/W4221161695","https://openalex.org/W4309953112","https://openalex.org/W4310290453","https://openalex.org/W4319165821","https://openalex.org/W4379089709","https://openalex.org/W4385327568","https://openalex.org/W4385567149","https://openalex.org/W4385571219","https://openalex.org/W4390833131","https://openalex.org/W4391631244","https://openalex.org/W4392637287","https://openalex.org/W4400373871","https://openalex.org/W4403324134","https://openalex.org/W4405254469","https://openalex.org/W4407794264","https://openalex.org/W4414037010","https://openalex.org/W4415798414","https://openalex.org/W4416037467","https://openalex.org/W4417097899","https://openalex.org/W7130388947","https://openalex.org/W7133192525","https://openalex.org/W7133209886","https://openalex.org/W7133223072","https://openalex.org/W7133224126","https://openalex.org/W7133228402","https://openalex.org/W7133231369","https://openalex.org/W7149001675"],"related_works":["https://openalex.org/W7130388947","https://openalex.org/W7163891199","https://openalex.org/W7163412604","https://openalex.org/W7119976813","https://openalex.org/W3023380900","https://openalex.org/W3169206174","https://openalex.org/W7115030330","https://openalex.org/W4403851143","https://openalex.org/W2398045853","https://openalex.org/W4248639100"],"abstract_inverted_index":{"This":[0],"thesis":[1,52],"studies":[2],"how":[3],"input":[4],"representations":[5],"and":[6,31,60,65,72,108,133,194,201,210],"supervised":[7],"reasoning":[8],"traces":[9],"affect":[10],"out-of-distribution":[11],"(OOD)":[12],"generalisation":[13],"in":[14,23],"FrozenLake":[15,17],"planning.":[16],"is":[18,117],"a":[19,25,28,33,84],"deterministic":[20],"grid-world":[21],"task":[22],"which":[24],"model":[26,86],"receives":[27],"complete":[29],"map":[30],"outputs":[32],"move":[34],"sequence":[35],"that":[36,176],"reaches":[37],"the":[38,79,92,127,173,206],"goal":[39],"while":[40],"avoiding":[41],"holes;":[42],"candidate":[43],"plans":[44],"can":[45,179],"be":[46],"checked":[47],"exactly":[48],"by":[49],"simulation.":[50],"The":[51],"extends":[53],"an":[54],"existing":[55],"benchmark":[56],"with":[57,104,119,185],"coordinate-based":[58,95,189],"inputs":[59],"trace":[61,192],"formats,":[62],"solution":[63],"augmentation,":[64],"structural":[66,141,215],"stress":[67],"tests":[68,77],"based":[69],"on":[70,101,110,146],"direction":[71],"turn":[73],"complexity.":[74],"It":[75],"also":[76],"whether":[78],"trace-supervision":[80],"findings":[81],"transfer":[82,162],"to":[83],"different":[85],"family.":[87],"Using":[88],"simulator-based":[89],"valid-plan":[90],"accuracy,":[91],"strongest":[93],"non-augmented":[94],"input\u2013trace":[96],"combinations":[97],"reach":[98,131],"0.83":[99],"accuracy":[100],"larger":[102],"maps":[103,147],"unseen":[105],"start-goal":[106],"distances":[107],"0.62":[109],"fixed-size":[111],"distance":[112,211],"extrapolation.":[113],"When":[114],"coordinate-description":[115],"supervision":[116,178],"augmented":[118],"all":[120],"optimal":[121],"paths":[122],"for":[123],"each":[124],"training":[125,196],"map,":[126],"corresponding":[128],"OOD":[129],"averages":[130],"0.91":[132],"0.85.":[134],"These":[135],"gains":[136,187],"do":[137],"not":[138],"imply":[139],"full":[140],"generalisation:":[142],"performance":[143],"drops":[144],"sharply":[145],"whose":[148],"shortest":[149],"solutions":[150,200],"require":[151],"more":[152,157],"distinct":[153],"movement":[154],"directions":[155],"or":[156],"turns.":[158],"Targeted":[159],"fine-tuning":[160],"improves":[161],"only":[163],"once":[164],"sufficiently":[165],"many":[166],"structurally":[167,202],"complex":[168],"examples":[169],"are":[170],"added.":[171],"Overall,":[172],"results":[174],"show":[175],"reasoning-trace":[177],"induce":[180],"useful":[181],"procedure-like":[182],"planning":[183],"behaviour,":[184],"substantial":[186],"from":[188],"representations,":[190],"structured":[191],"formats":[193],"broader":[195],"coverage":[197],"of":[198],"valid":[199],"difficult":[203],"examples.":[204],"At":[205],"same":[207],"time,":[208],"size":[209],"extrapolation":[212],"alone":[213],"overestimates":[214],"robustness.":[216]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-23T00:00:00"}