{"id":"W3143003892","doi":"10.3390/app11073068","title":"New Approach in Human-AI Interaction by Reinforcement-Imitation Learning","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Imitation; Action (physics); Artificial intelligence; Process (computing); Asynchronous communication; Psychology; Social psychology","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":[0.0008605304,0.0006581546,0.0005535611,0.0004589129,0.0003953435,0.0009019069,0.001500169,0.001024149,0.002359848],"category_scores_gemma":[0.001390953,0.0002808952,0.000617833,0.0002867206,0.001246374,0.00113555,0.001265736,0.001137721,0.0005740386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005219832,"about_ca_system_score_gemma":0.0007126376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001518214,"about_ca_topic_score_gemma":0.001118419,"domain_scores_codex":[0.9994288,0.0002013498,0.00002671694,0.0001362959,0.0001688795,0.0000379523],"domain_scores_gemma":[0.9995851,0.0001943672,0.00004276564,0.0000639572,0.00007315086,0.00004069778],"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":[0.0001385324,0.0002259368,0.001708994,0.0004217004,0.0002006016,0.000428137,0.0007177965,0.456387,0.01647153,0.2663206,0.004172238,0.2528068],"study_design_scores_gemma":[0.00002431276,0.00009460658,0.0001786707,0.00002027995,0.00002033258,0.0001101774,0.00003141775,0.9542393,0.001890847,0.03405979,0.009312705,0.00001755373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004933686,0.0006502968,0.9879159,0.0003913438,0.00008163377,0.00003908473,0.00001087783,0.0003477742,0.005629404],"genre_scores_gemma":[0.5465382,0.001178858,0.4387815,0.0003080069,0.000195068,0.0002667922,0.00005555934,0.0001313164,0.01254456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002359848,"threshold_uncertainty_score":0.007894456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03262796757263529,"score_gpt":0.2980415984961594,"score_spread":0.2654136309235241,"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."}}