{"id":"W200360931","doi":"","title":"Turning lights out with DQ-learning","year":2006,"lang":"en","type":"article","venue":"International conference on Artificial intelligence and applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Discretization; Premise; Arity; Overhead (engineering); Byte; Table (database); Representation (politics); Reinforcement learning; Artificial intelligence; State (computer science); Algorithm; Theoretical computer science; Mathematics; Discrete mathematics; Programming language; Database","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":[0.0001301312,0.0001523785,0.0001088697,0.0001438569,0.0002740821,0.0005206705,0.00062252,0.00005161226,0.00007773738],"category_scores_gemma":[0.00002266793,0.0001323935,0.00002961998,0.0001901523,0.0001045304,0.0003021413,0.0001028574,0.0002631455,0.000328232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003701281,"about_ca_system_score_gemma":0.00005081029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003978351,"about_ca_topic_score_gemma":0.00003733621,"domain_scores_codex":[0.9987136,0.00002693392,0.000300546,0.0003957851,0.0003600071,0.000203195],"domain_scores_gemma":[0.999168,0.000106721,0.0001563935,0.0002505161,0.0002548742,0.00006346013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006406622,0.00003602434,0.0002146389,0.000002049077,0.000009449975,0.000002345949,0.0001363365,0.08858942,0.0008575185,0.8825097,0.00002538601,0.02761072],"study_design_scores_gemma":[0.00005962301,0.0002279113,0.0004598377,0.00007818531,0.00001026656,0.00001431538,0.000368784,0.8298621,0.01511391,0.1270107,0.02636423,0.000430098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00124074,0.000009610243,0.9429966,0.001973202,0.0001103673,0.000185942,0.000001255865,0.0001550614,0.0533272],"genre_scores_gemma":[0.9892534,0.00002896745,0.008375598,0.0001412903,0.0002194096,0.00009754885,0.0000198322,0.000009332684,0.00185461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9880127,"threshold_uncertainty_score":0.5398852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06063246829204915,"score_gpt":0.308802611147818,"score_spread":0.2481701428557688,"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."}}