{"id":"W4362590700","doi":"10.1016/j.cviu.2023.103689","title":"Tractable large-scale deep reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Code (set theory); Stability (learning theory); Machine learning; Deep learning; Scale (ratio); Supervised learning; Artificial neural network; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000187481,0.0001260799,0.00012418,0.0001798534,0.0002745758,0.0001756167,0.00005249055,0.00005980343,0.00006003232],"category_scores_gemma":[0.000004149281,0.000117927,0.00003712486,0.0002489076,0.0000172624,0.000369762,0.00005602917,0.0001827897,0.00007654138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020453,"about_ca_system_score_gemma":0.000003003032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.735886e-7,"about_ca_topic_score_gemma":0.000001057934,"domain_scores_codex":[0.9992542,0.00001424154,0.000155271,0.0001614002,0.0001285047,0.0002863861],"domain_scores_gemma":[0.9997658,0.00004433842,0.00002430985,0.00008216331,0.00001124742,0.00007220184],"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":[0.00003866551,0.00005723548,0.000370012,0.0005161862,0.0001253713,0.0001358068,0.006410614,0.8112322,0.0779052,0.002728455,0.05521201,0.04526822],"study_design_scores_gemma":[0.0003499834,0.00005231985,0.0003337016,0.00007259568,0.000007179295,0.00001341497,0.0008496494,0.9911938,0.0005386721,0.0002019149,0.006233593,0.000153146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03739414,0.0000674007,0.9575758,0.00006218009,0.0004760108,0.00007638716,4.045985e-7,0.001400191,0.002947454],"genre_scores_gemma":[0.9965464,0.000261934,0.002763338,0.0000320353,0.0001050632,0.00000219462,0.00002156348,0.00002824304,0.0002392576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9591522,"threshold_uncertainty_score":0.4808925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01601594838514524,"score_gpt":0.2455244141669861,"score_spread":0.2295084657818408,"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."}}