{"id":"W2964469479","doi":"","title":"Understanding the Relation Between Maximum-Entropy Inverse Reinforcement Learning and Behaviour Cloning.","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Principle of maximum entropy; Cloning (programming); Artificial intelligence; Computer science; Relation (database); Inverse; Entropy (arrow of time); Mathematics; Machine learning; Data mining; Physics; Thermodynamics","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":[0.0005207479,0.000201213,0.0001647496,0.0002684733,0.0005541941,0.0007066284,0.0006778677,0.00008962461,0.0003624565],"category_scores_gemma":[0.0003753715,0.0001778774,0.00007485493,0.000276397,0.0000992838,0.0007333627,0.0003640385,0.0009185713,0.0002879362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002562065,"about_ca_system_score_gemma":0.00008076348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005631406,"about_ca_topic_score_gemma":0.000003193406,"domain_scores_codex":[0.9977406,0.0002344445,0.00041385,0.0004937571,0.0008252705,0.0002921347],"domain_scores_gemma":[0.9984158,0.0005586263,0.0003910572,0.0003441362,0.0001976184,0.0000927928],"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":[0.000009659366,0.000006086881,0.2304466,0.000004130556,0.00005825371,0.000003306779,0.002115101,0.5475546,0.0002835965,0.2190419,0.00007723915,0.0003994886],"study_design_scores_gemma":[0.0006801739,0.0002447456,0.0585156,0.00009689059,0.00002522459,0.000010492,0.002387169,0.9310957,0.00008713722,0.005112426,0.001475852,0.000268652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04894954,0.000005737455,0.8974964,0.004103926,0.0005940521,0.0003921388,7.994494e-7,0.0002307291,0.0482267],"genre_scores_gemma":[0.9870116,0.00005244823,0.001936415,0.0001110747,0.00008419365,0.00002151569,0.00006707069,0.00001802834,0.01069762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9380621,"threshold_uncertainty_score":0.725363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0945946462711303,"score_gpt":0.3266313768676395,"score_spread":0.2320367305965092,"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."}}