{"id":"W2909590401","doi":"10.1109/ism.2018.00025","title":"Deep Reinforcement Learning with Parameterized Action Space for Object Detection","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Parameterized complexity; Discriminative model; Pascal (unit); Object detection; Markov decision process; Machine learning; Cognitive neuroscience of visual object recognition; Object (grammar); Contextual image classification; Pattern recognition (psychology); Markov process; Image (mathematics); Mathematics; Algorithm","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":[0.00007640554,0.00008877965,0.00007523594,0.00004559181,0.000297226,0.00006411605,0.0001786266,0.00002803659,0.000009640805],"category_scores_gemma":[0.00002255472,0.00007115328,0.00002627991,0.0003184771,0.00003503264,0.0003773162,0.00004958879,0.00007026711,0.00003320926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005021529,"about_ca_system_score_gemma":0.00001205403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008858922,"about_ca_topic_score_gemma":0.00007884562,"domain_scores_codex":[0.9992928,0.00001838124,0.0001057138,0.0002753951,0.0001107834,0.0001969628],"domain_scores_gemma":[0.999396,0.00009179633,0.00009088156,0.0002767414,0.00009885772,0.00004570321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000394666,0.00005003306,0.00009695975,0.00002423617,0.00005617847,0.000001003497,0.0006491151,0.2338959,0.1571599,0.03910817,0.0002051963,0.5683586],"study_design_scores_gemma":[0.0003498123,0.0006739014,0.00009475793,0.000003996855,0.000004974823,0.000009321857,0.00002566868,0.8694792,0.1190188,0.001023938,0.009197564,0.0001180227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006867005,0.00000293606,0.9909791,0.000247859,0.0001014024,0.0004292578,2.17906e-8,0.0003290932,0.001043353],"genre_scores_gemma":[0.767238,0.00000410408,0.2315532,0.000103628,0.00009113998,0.0001690912,0.000001199069,0.000007282002,0.0008323462],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.760371,"threshold_uncertainty_score":0.2901547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02654629509425886,"score_gpt":0.2850630055896012,"score_spread":0.2585167104953424,"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."}}