{"id":"W7124181186","doi":"10.65109/apft3995","title":"Expectation-Maximization for Inverse Reinforcement Learning with Hidden Data","year":2016,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Missing data; Reinforcement learning; Task (project management); Trajectory; Feature (linguistics); Key (lock); State space; State (computer science); Sorting","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"],"consensus_categories":[],"category_scores_codex":[0.0007865781,0.0004475788,0.0003548453,0.0002637644,0.0005928982,0.0005512045,0.002500622,0.0001519504,0.0007109274],"category_scores_gemma":[0.0009349517,0.0003026421,0.00007102088,0.0005889045,0.0001832408,0.003716293,0.001295415,0.0001902205,0.0003111999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002462042,"about_ca_system_score_gemma":0.0005016364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003316769,"about_ca_topic_score_gemma":0.00002239016,"domain_scores_codex":[0.99602,0.0001393527,0.0008384814,0.001253268,0.0009402005,0.0008086726],"domain_scores_gemma":[0.9954033,0.0006693319,0.0007406207,0.002356217,0.0005818061,0.0002487462],"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":[0.0001287956,0.0000288643,0.001883794,0.00007597026,0.0001578039,0.000004899611,0.001623943,0.9378918,0.0002080323,0.01576092,0.00363481,0.03860034],"study_design_scores_gemma":[0.002680855,0.001210554,0.0001358341,0.000306339,0.00008057061,0.000007505416,0.0004103833,0.9791949,0.0005339357,0.00008309206,0.01476154,0.0005944739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003114969,0.00002209763,0.9900202,0.002260161,0.0005937137,0.001236853,0.000003946881,0.0002738496,0.00527773],"genre_scores_gemma":[0.6345196,0.0002144783,0.2912707,0.0004201512,0.0003238992,0.00008603158,0.0001923017,0.00008114443,0.07289169],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6987495,"threshold_uncertainty_score":0.9999425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04984481620274459,"score_gpt":0.2751606179449554,"score_spread":0.2253158017422109,"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."}}