{"id":"W7124298994","doi":"10.65109/nind4053","title":"Do As You Teach: A Multi-Teacher Approach to Self-Play in Deep Reinforcement Learning","year":2023,"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 Alberta; Institut national de psychiatrie légale Philippe-Pinel","funders":"","keywords":"Reinforcement learning; Automation; Robot; State (computer science); Task (project management); Robotics; Robot learning; Train","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":[0.001587298,0.0007860584,0.0007532426,0.0002952078,0.0004286458,0.0008632944,0.002115576,0.001302587,0.004865607],"category_scores_gemma":[0.003302426,0.0004422821,0.000334998,0.0002780888,0.001062805,0.001554654,0.001963888,0.002475133,0.0005597979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001085413,"about_ca_system_score_gemma":0.001002395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00288852,"about_ca_topic_score_gemma":0.004200993,"domain_scores_codex":[0.9995055,0.000236319,0.00001762597,0.00008976955,0.00008688583,0.00006393803],"domain_scores_gemma":[0.9990314,0.0005338668,0.00009607058,0.00009891225,0.0001117318,0.0001280134],"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":[0.0004050572,0.0005137667,0.001967387,0.0001868256,0.0001239807,0.0001673316,0.0005014251,0.6630226,0.004274179,0.1071324,0.00735721,0.2143479],"study_design_scores_gemma":[0.00001635201,0.00003505863,0.00004969353,0.000007082573,0.000005970128,0.000007907385,0.000009091646,0.9821218,0.0003299676,0.01671237,0.0007008272,0.000003784941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01398118,0.0003447566,0.9803816,0.0007942253,0.00007592536,0.00006265783,0.00004294122,0.0005277925,0.003788919],"genre_scores_gemma":[0.8173906,0.0002723385,0.1735425,0.0003694777,0.00009322516,0.0002474697,0.00006585855,0.0001686977,0.007849826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004865607,"threshold_uncertainty_score":0.01627713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0385510444796588,"score_gpt":0.2879504930576487,"score_spread":0.2493994485779899,"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."}}