{"id":"W4403906488","doi":"10.1007/978-3-031-73033-7_9","title":"Learning to Drive via Asymmetric Self-Play","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Human–computer interaction; Artificial intelligence","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001204857,0.0007622988,0.0006457323,0.003004241,0.0003602479,0.001479997,0.00482234,0.0004133996,0.00002610008],"category_scores_gemma":[0.0002187765,0.0007209025,0.0001981459,0.002807312,0.0002655677,0.0006068602,0.003579728,0.002198316,0.001457624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007833436,"about_ca_system_score_gemma":0.0004981015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001546442,"about_ca_topic_score_gemma":0.000009632256,"domain_scores_codex":[0.9941204,0.00004372432,0.0007070813,0.002229756,0.001818402,0.001080681],"domain_scores_gemma":[0.9967394,0.0007401116,0.000286093,0.001549614,0.0003097407,0.0003750043],"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":[0.000001335149,0.000007801553,0.00003170535,0.00004094688,0.00002158109,0.0001382156,0.001668141,0.7821914,0.0000326027,0.01248607,0.00003828821,0.2033419],"study_design_scores_gemma":[0.0001281772,0.0005204755,0.00004714708,0.0004215443,0.00001825795,0.00008813402,2.618027e-7,0.9589888,0.000402901,0.0230221,0.01547357,0.00088863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001758368,0.0002613934,0.9725831,0.0007881108,0.003715329,0.0005282825,8.871849e-7,0.000827196,0.02127814],"genre_scores_gemma":[0.1266716,0.00006342736,0.8597542,0.002436509,0.001027223,0.00002065299,0.00000724119,0.0001353676,0.009883733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2024533,"threshold_uncertainty_score":0.9995565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00983572967448916,"score_gpt":0.239412937519269,"score_spread":0.2295772078447798,"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."}}