{"id":"W2964191931","doi":"","title":"Unsupervised Video Object Segmentation for Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Segmentation; Representation (politics); Object (grammar); Motion (physics); Code (set theory); Unsupervised learning; Object detection; Focus (optics); Computer vision; Action (physics); Suite; Feature learning; Deep learning; Machine learning; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002904538,0.0001772299,0.0001491184,0.0001796665,0.0004486252,0.0001223472,0.0007641474,0.00007584065,0.00007805285],"category_scores_gemma":[0.0000905545,0.0002030103,0.0001047753,0.0006056595,0.00009177024,0.0008063128,0.0002500259,0.0001377198,0.0002187755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001847125,"about_ca_system_score_gemma":0.00006394438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002287341,"about_ca_topic_score_gemma":0.000008726201,"domain_scores_codex":[0.9986928,0.00007475536,0.0001965931,0.0005184315,0.0001181781,0.000399308],"domain_scores_gemma":[0.9988548,0.0001446157,0.0001652235,0.0004855925,0.0002339621,0.0001158133],"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":[0.00003312266,0.00001090117,0.00139243,0.00001561546,0.00003621346,0.000007618895,0.0005806465,0.950289,0.0005049824,0.04613548,0.0001289401,0.0008650952],"study_design_scores_gemma":[0.001030969,0.0005244291,0.0002990545,0.00001676719,0.00002654522,0.000001873199,0.0002067649,0.9926014,0.002185771,0.0006556768,0.002205881,0.0002448885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0208034,0.000005850268,0.9739411,0.00005204257,0.0003079886,0.0003621004,1.792432e-7,0.0002610938,0.004266252],"genre_scores_gemma":[0.9845117,0.00001865635,0.01015042,0.000202205,0.00009709257,0.00000212579,0.00001244443,0.0000150941,0.004990256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9637907,"threshold_uncertainty_score":0.8278521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0505535799427427,"score_gpt":0.202873746225006,"score_spread":0.1523201662822633,"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."}}