{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001566902,0.00122024,0.001413238,0.0004488206,0.0004059966,0.0008800267,0.002225241,0.001397936,0.003678383],"category_scores_gemma":[0.00562928,0.0006953441,0.000717595,0.0003336142,0.001206059,0.001376939,0.002256623,0.002451075,0.000804481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008662162,"about_ca_system_score_gemma":0.001768906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003964559,"about_ca_topic_score_gemma":0.005016447,"domain_scores_codex":[0.9994053,0.0002023509,0.00002872076,0.0001459305,0.0001324194,0.00008534191],"domain_scores_gemma":[0.9982615,0.001072327,0.0001489161,0.0002361194,0.0001559606,0.0001251785],"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":[0.0001239491,0.0001021573,0.0007774272,0.00009720742,0.00006131813,0.00008341508,0.00006066423,0.9271407,0.001909659,0.005604821,0.001833268,0.06220553],"study_design_scores_gemma":[0.00001352903,0.00002339111,0.00003277231,0.000004509436,0.000003505083,0.000007113125,0.000002768413,0.9971766,0.0002899214,0.00223144,0.0002112158,0.000003170662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02467012,0.0005273281,0.9671612,0.0003514877,0.00008818153,0.0001073397,0.0001232691,0.004477574,0.002493581],"genre_scores_gemma":[0.8406559,0.000179441,0.1552905,0.0004047577,0.00005504995,0.0003391592,0.0002946946,0.0003657138,0.002414817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003964559,"threshold_uncertainty_score":0.01230544,"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."}}