{"id":"W2971218263","doi":"","title":"SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Meta learning (computer science); Scalability; Machine learning; Principle of maximum entropy; Context (archaeology); Task (project management)","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000479515,0.0002906749,0.0003951013,0.0002214863,0.0004259998,0.001534605,0.000732367,0.000118044,0.00007511479],"category_scores_gemma":[0.00009300755,0.0002495022,0.0001276993,0.0005611135,0.00006343841,0.01147099,0.0002344334,0.0003744723,0.001006312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001513373,"about_ca_system_score_gemma":0.0001563682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000200862,"about_ca_topic_score_gemma":8.307445e-7,"domain_scores_codex":[0.9973108,0.00009596322,0.0009220708,0.0002425263,0.0009498176,0.0004788594],"domain_scores_gemma":[0.9981554,0.00008780984,0.0008239458,0.0004113584,0.0004256564,0.0000958301],"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":[0.000004263585,0.000004655413,0.0003051716,0.0002864987,0.00007217233,6.324762e-7,0.003274079,0.9698951,0.00006967596,0.02324877,0.002186974,0.0006520445],"study_design_scores_gemma":[0.0005026505,0.0001204734,0.0001208743,0.00008205771,0.00003932692,0.00003860941,0.001239394,0.9491941,0.0002847671,0.00006688205,0.04801928,0.0002915778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004195794,0.0001806129,0.9541455,0.0004447066,0.001170226,0.000764259,0.00000221465,0.0006914553,0.03840524],"genre_scores_gemma":[0.990599,0.000008758606,0.001352624,0.001802637,0.00007675293,0.00007141324,0.00009813909,0.00001350375,0.005977126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9864032,"threshold_uncertainty_score":0.9999957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03388311419550946,"score_gpt":0.2615376253999302,"score_spread":0.2276545112044207,"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."}}