{"id":"https://openalex.org/W4401201822","doi":"https://doi.org/10.48550/arxiv.2407.19532","title":"The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited","display_name":"The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited","publication_year":2024,"publication_date":"2024-07-28","ids":{"openalex":"https://openalex.org/W4401201822","doi":"https://doi.org/10.48550/arxiv.2407.19532"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.19532","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19532","pdf_url":"https://arxiv.org/pdf/2407.19532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.19532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Eaton, Kenneth","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4388482740","display_name":"Georgia Tech Research Institute","ror":"https://ror.org/04qfrh333","country_code":null,"type":"facility","lineage":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Eaton, Kenneth","raw_affiliation_strings":["Georgia Tech Research Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Research Institute ,","institution_ids":["https://openalex.org/I4388482740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077808473","display_name":"Jonathan Balloch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balloch, Jonathan","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101854617","display_name":"Julia Kim","orcid":"https://orcid.org/0000-0002-3052-0555","observed_orcids":["https://orcid.org/0000-0002-3052-0555"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, Julia","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061883150","display_name":"Mark Owen Riedl","orcid":"https://orcid.org/0000-0001-5283-6588","observed_orcids":["https://orcid.org/0000-0001-5283-6588"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riedl, Mark","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9965999722480774,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9965999722480774,"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":0.003100000089034438,"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":0.0,"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/interpretability","display_name":"interpretability","score":0.9150000214576721},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.8320000171661377},{"id":"https://openalex.org/keywords/codebook","display_name":"codebook","score":0.9169999957084656},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9919999837875366}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9331673383712769},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8321360349655151},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5985360741615295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631400942802429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5357934832572937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.472040057182312},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25470030307769775},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06703117489814758}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.19532","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19532","pdf_url":"https://arxiv.org/pdf/2407.19532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.19532","doi":"https://doi.org/10.48550/arxiv.2407.19532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.19532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.19532","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19532","pdf_url":"https://arxiv.org/pdf/2407.19532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401201822.pdf","grobid_xml":"https://content.openalex.org/works/W4401201822.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1986582023","https://openalex.org/W2961085424","https://openalex.org/W2966829450","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Interpretability":[0],"of":[1,66,75,86],"deep":[2],"reinforcement":[3,51,58],"learning":[4,59],"systems":[5],"could":[6],"assist":[7],"operators":[8],"with":[9,14],"understanding":[10],"how":[11],"they":[12],"interact":[13],"their":[15],"environment.":[16],"Vector":[17],"quantization":[18,44,68,99],"methods":[19,24],"--":[20,25],"also":[21],"called":[22],"codebook":[23],"discretize":[26],"a":[27,79],"neural":[28],"network's":[29],"latent":[30],"space":[31],"that":[32,63],"is":[33],"often":[34],"suggested":[35],"to":[36],"yield":[37],"emergent":[38],"interpretability.":[39,92,106],"We":[40,93],"investigate":[41],"whether":[42],"vector":[43,67,98],"in":[45,49,56],"fact":[46],"provides":[47],"interpretability":[48],"model-based":[50],"learning.":[52],"Our":[53],"experiments,":[54],"conducted":[55],"the":[57,64],"environment":[60],"Crafter,":[61],"show":[62],"codes":[65],"models":[69],"are":[70,88],"inconsistent,":[71],"have":[72,78],"no":[73],"guarantee":[74],"uniqueness,":[76],"and":[77],"limited":[80],"impact":[81],"on":[82,96],"concept":[83],"disentanglement,":[84],"all":[85],"which":[87],"necessary":[89],"traits":[90],"for":[91,104],"share":[94],"insights":[95],"why":[97],"may":[100],"be":[101],"fundamentally":[102],"insufficient":[103],"model":[105]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2025-10-10T00:00:00"}