{"id":"W6979290938","doi":"","title":"A Smooth Sea Never Made a Skilled $\\texttt{SAILOR}$: Robust Imitation via Learning to Search","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Canada Excellence Research Chairs, Government of Canada; National Science Foundation","keywords":"Mistake; Set (abstract data type); Imitation; Outcome (game theory); Code (set theory); Task (project management); Plan (archaeology); Process (computing); Test (biology); Component (thermodynamics); Expert system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001158443,0.001344558,0.001105561,0.0004756573,0.0004582535,0.0009033896,0.003020503,0.001586061,0.004388047],"category_scores_gemma":[0.00647841,0.0006225399,0.0006944583,0.000340285,0.001262356,0.001901082,0.001861571,0.002459558,0.001994406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009673371,"about_ca_system_score_gemma":0.001478624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01008811,"about_ca_topic_score_gemma":0.008815282,"domain_scores_codex":[0.9992898,0.0001718822,0.0000356341,0.0002530022,0.0001433686,0.0001062576],"domain_scores_gemma":[0.9978393,0.001120721,0.0001666629,0.0005208586,0.0002102435,0.0001422088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005015997,0.0003535057,0.002896142,0.0004888803,0.0001432539,0.0002576993,0.0002354451,0.6136684,0.01885521,0.009919968,0.01247365,0.3402062],"study_design_scores_gemma":[0.00003047183,0.0001095308,0.000291197,0.0000180602,0.00001181289,0.00003995165,0.00002143011,0.9909561,0.003752597,0.003431205,0.001324576,0.00001298379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2196998,0.00215783,0.7257413,0.001165127,0.0002749544,0.0002370861,0.0006820266,0.03433262,0.01570937],"genre_scores_gemma":[0.8089317,0.0003419977,0.1778572,0.0003611073,0.00004592112,0.0002392925,0.001209125,0.001398988,0.009614713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01008811,"threshold_uncertainty_score":0.02005881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04761884207748829,"score_gpt":0.2007396210769313,"score_spread":0.153120778999443,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}