{"id":"W2174786457","doi":"10.48550/arxiv.1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Exploit; Artificial intelligence; Transfer of learning; Set (abstract data type); Task (project management); Machine learning; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004393147,0.0004550408,0.0004196315,0.0003037256,0.0002267781,0.0002756433,0.001556099,0.0003733191,0.00003523204],"category_scores_gemma":[0.00008195826,0.0005224983,0.0001596511,0.0003528064,0.0001470049,0.000578645,0.002137219,0.001185823,0.0001062439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003332755,"about_ca_system_score_gemma":0.0002078969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009791936,"about_ca_topic_score_gemma":0.00001593515,"domain_scores_codex":[0.9976581,0.0001763913,0.0003109058,0.001103297,0.0002206087,0.0005307141],"domain_scores_gemma":[0.9980758,0.0001141297,0.000180699,0.001043803,0.0002419605,0.0003436219],"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":[0.00001989643,0.00001524419,0.001644316,0.0000749872,0.00009771503,0.00009938002,0.0008383752,0.9728162,0.00002740382,0.02389677,0.00007999845,0.0003897577],"study_design_scores_gemma":[0.0007869599,0.0001416586,0.000284112,0.00008431375,0.00007446969,0.000005761398,0.0001428235,0.9946031,0.00006847557,0.001025683,0.002199968,0.0005826941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05056662,0.0000724946,0.9436437,0.00005909443,0.0005010002,0.0003599242,0.000001085686,0.0003674588,0.004428579],"genre_scores_gemma":[0.9930797,0.0003131168,0.002293247,0.00008640963,0.00006315284,0.000001270768,0.00002706163,0.00003075128,0.00410533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.942513,"threshold_uncertainty_score":0.9997227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07661995159032055,"score_gpt":0.1959416640452457,"score_spread":0.1193217124549251,"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."}}