{"id":"W4406132533","doi":"10.1007/s00521-024-10829-4","title":"Do as you teach: a multi-teacher approach to self-play in deep reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Context (archaeology); Curriculum; Reinforcement; Computational Science and Engineering; Artificial intelligence; State space; Space (punctuation); Baseline (sea); Mathematics education; Machine learning; Psychology; Pedagogy; Mathematics","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":[0.0003796594,0.0001813386,0.0001818949,0.0002354277,0.0003925006,0.0002766646,0.0006192388,0.00006983408,0.00000192639],"category_scores_gemma":[0.00006064286,0.0001835248,0.00003973789,0.0008394683,0.00002704171,0.0001184933,0.0005562141,0.0004684703,0.00003287627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007653617,"about_ca_system_score_gemma":0.00003698978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004211249,"about_ca_topic_score_gemma":0.000001242805,"domain_scores_codex":[0.9984543,0.00008784165,0.0003570283,0.0005522802,0.0001944171,0.000354095],"domain_scores_gemma":[0.9991861,0.0001102222,0.00009904493,0.0004470603,0.00005343304,0.0001041458],"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":[0.000001550406,0.00005930579,0.005011878,0.00002226554,0.00001023998,5.448379e-7,0.001596976,0.9491836,0.00006398511,0.02399057,0.00004872941,0.02001031],"study_design_scores_gemma":[0.0003504591,0.000043083,0.004084371,0.00002587138,0.00000716409,0.000005991801,0.0001967782,0.986515,0.0000310054,0.00006456093,0.008499518,0.0001762273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01368494,0.00007077138,0.9703644,0.0003951334,0.00005400129,0.0006362356,5.231239e-8,0.0003517999,0.01444267],"genre_scores_gemma":[0.9298639,0.000006761934,0.06791709,0.000450557,0.00004086289,0.00008486943,0.000005714518,0.000009879185,0.001620387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9161789,"threshold_uncertainty_score":0.7483924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0195471957952896,"score_gpt":0.2921890384630919,"score_spread":0.2726418426678023,"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."}}