{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006581427,0.0001284392,0.0001363064,0.0001672616,0.0003442016,0.0005679623,0.0006796431,0.00005568448,0.00007587433],"category_scores_gemma":[0.00005890165,0.0001302049,0.00003125461,0.001178146,0.00006934397,0.0008858094,0.0002343036,0.0003117341,0.00007988205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008321628,"about_ca_system_score_gemma":0.0001592839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004541756,"about_ca_topic_score_gemma":0.000004760884,"domain_scores_codex":[0.9982195,0.00006132944,0.0003165943,0.000522879,0.0005451728,0.0003344508],"domain_scores_gemma":[0.9993831,0.00009720734,0.0001531083,0.0002506399,0.00004296048,0.00007296333],"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":[0.00000138217,0.00001340917,0.0005491838,0.000006830862,0.000003975551,0.00000148045,0.00108597,0.8786363,0.01045766,0.1015311,0.002662207,0.005050478],"study_design_scores_gemma":[0.0005737732,0.00009423082,0.0004378788,0.00002748711,0.00000488942,0.000008753385,0.001694205,0.9679015,0.015356,0.001792942,0.01174808,0.0003603141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00313677,0.00002134484,0.8681174,0.0003493534,0.0001545108,0.0001095382,3.585717e-8,0.00009375992,0.1280173],"genre_scores_gemma":[0.9436489,0.000009146657,0.05074633,0.0004316013,0.00003793322,0.00001513624,0.00001772051,0.000005905364,0.005087352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9405121,"threshold_uncertainty_score":0.5476874,"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."}}