{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003728325,0.0002147989,0.0002123531,0.0005474041,0.0003643505,0.0001812966,0.001142844,0.0001119527,0.00006622619],"category_scores_gemma":[0.0001348805,0.0002535292,0.0001112603,0.002239492,0.00006116521,0.0009073977,0.0007253897,0.0004196836,0.0006038981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002963948,"about_ca_system_score_gemma":0.0001516959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000102736,"about_ca_topic_score_gemma":0.00001248987,"domain_scores_codex":[0.9981884,0.0002093806,0.0002018079,0.0007182317,0.0001718805,0.0005103448],"domain_scores_gemma":[0.9986463,0.0002148877,0.00008937201,0.0006511224,0.000213669,0.0001846478],"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":[0.00002855267,0.00002766323,0.00557383,0.0000199588,0.00003730936,0.00005678019,0.0006135878,0.9577163,0.0002146958,0.03387177,0.0004603737,0.00137913],"study_design_scores_gemma":[0.000657777,0.0001249907,0.007233213,0.00005052233,0.00002361726,0.000001698877,0.0002554233,0.9878001,0.0002265385,0.0004968451,0.002860778,0.0002684589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06975389,0.000007659743,0.9221871,0.0005658383,0.00024595,0.0002823753,3.857349e-7,0.000294072,0.006662707],"genre_scores_gemma":[0.9604812,0.00001501895,0.008086095,0.0005202331,0.00002592895,0.000001131914,0.000005499411,0.00001456839,0.03085035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.914101,"threshold_uncertainty_score":0.9999917,"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."}}