{"id":"https://openalex.org/W7225174153","doi":"https://doi.org/10.48550/arxiv.2611.03091","title":"KlaskTron-IL: A Contact-Rich Adversarial Imitation Learning Benchmark with a Validated Sim-to-Real Bridge","display_name":"KlaskTron-IL: A Contact-Rich Adversarial Imitation Learning Benchmark with a Validated Sim-to-Real Bridge","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225174153","doi":"https://doi.org/10.48550/arxiv.2611.03091"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03091","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03091","pdf_url":"https://arxiv.org/pdf/2611.03091","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":null,"license_id":null,"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/2611.03091","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140338282","display_name":"Nicklas Sohm","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sohm, Nicklas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087505557","display_name":"Aswin Ramachandran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramachandran, Aswin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050557198","display_name":"Raffaello D\u2019andrea B","orcid":"https://orcid.org/0000-0001-5287-7849","observed_orcids":["https://orcid.org/0000-0001-5287-7849"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D'Andrea, Raffaello","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot 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/adversarial-imitation-learning","display_name":"adversarial imitation learning","score":0.8629999756813049},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.9070000052452087},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.4880000054836273},{"id":"https://openalex.org/keywords/behavioral-cloning","display_name":"behavior cloning","score":0.5630000233650208},{"id":"https://openalex.org/keywords/generative-adversarial-imitation-learning","display_name":"generative adversarial imitation learning","score":0.9200000166893005}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7516000270843506},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6960999965667725},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6452000141143799},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068999767303467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040999889373779},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3952000141143799},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.36309999227523804},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.34299999475479126},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03091","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03091","pdf_url":"https://arxiv.org/pdf/2611.03091","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.03091","doi":"https://doi.org/10.48550/arxiv.2611.03091","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03091","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.03091","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03091","pdf_url":"https://arxiv.org/pdf/2611.03091","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204777077","https://openalex.org/W3008208113","https://openalex.org/W7124284875","https://openalex.org/W3082790045","https://openalex.org/W4416749157","https://openalex.org/W3199562506","https://openalex.org/W3210354864","https://openalex.org/W2740210681","https://openalex.org/W3001609349","https://openalex.org/W7164001748"],"abstract_inverted_index":{"KlaskTron":[0],"is":[1,116],"an":[2,102],"open-hardware":[3],"physical":[4,44,137],"platform":[5],"for":[6,143],"two-player":[7],"adversarial":[8,78],"reinforcement":[9],"learning,":[10],"with":[11],"a":[12,31,96,126],"learned":[13],"actuator":[14,121,155],"model":[15,122],"that":[16,66],"supports":[17],"zero-shot":[18,142],"sim-to-real":[19],"transfer":[20],"of":[21,72],"trained":[22,128],"policies.":[23],"Building":[24],"on":[25,42,129,135],"this":[26,114,130],"platform,":[27],"we":[28,140],"contribute":[29],"KlaskTron-IL:":[30],"multi-tier":[32],"imitation":[33],"learning":[34],"dataset":[35],"(80k":[36],"human":[37],"demonstration":[38],"timesteps":[39],"collected":[40],"directly":[41],"the":[43,59,109,117,120,136,144,154],"robot,":[45,138],"320k":[46],"symmetry-augmented":[47],"timesteps,":[48],"and":[49,63,101],"synthetic":[50],"expert":[51],"trajectories":[52],"up":[53],"to":[54,124],"5M":[55],"steps":[56],"generated":[57],"by":[58],"zero-shot-validated":[60],"PPO":[61],"policy),":[62],"diagnostic":[64],"baselines":[65],"expose":[67],"three":[68],"characteristic":[69],"failure":[70],"modes":[71],"standard":[73],"IL":[74],"methods":[75],"under":[76,99],"contact-rich":[77],"dynamics:":[79],"BC's":[80],"data":[81],"scaling":[82],"plateau,":[83],"GAIL's":[84],"interpretable":[85],"but":[86,95],"weak-gradient":[87],"discriminator":[88],"(Spearman":[89],"$\u03c1=":[90],"-1.0$":[91],"peg-ball":[92],"proximity":[93],"recovery,":[94],"logit":[97],"span":[98],"0.1),":[100],"asymmetric":[103],"BC-prior":[104],"x":[105],"reward-density":[106],"interaction.":[107],"Because":[108],"policy":[110,127],"interface":[111],"used":[112],"throughout":[113],"paper":[115],"same":[118],"one":[119],"bridges":[123],"hardware,":[125],"benchmark":[131],"can":[132],"run":[133],"unchanged":[134],"as":[139,150],"demonstrate":[141],"strongest":[145],"BC":[146],"baseline,":[147],"so":[148],"long":[149],"its":[151],"commands":[152],"respect":[153],"model's":[156],"$\\pm":[157],"0.2$":[158],"m/s":[159],"identification":[160],"range.":[161]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}