{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002315599,0.0005457282,0.0009947645,0.000279933,0.000564226,0.001349765,0.001418136,0.001308634,0.00582947],"category_scores_gemma":[0.01322405,0.0003800158,0.0005167843,0.0004034168,0.00249583,0.00332776,0.0022567,0.00321829,0.00108215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009312574,"about_ca_system_score_gemma":0.001340366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00228812,"about_ca_topic_score_gemma":0.00152114,"domain_scores_codex":[0.9986479,0.0005859792,0.00006533159,0.0002738941,0.0003204018,0.0001065208],"domain_scores_gemma":[0.9961099,0.002243199,0.0001886977,0.0007777048,0.0004769322,0.0002036417],"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":[0.0002759638,0.000143537,0.001444589,0.0002171667,0.0000935095,0.0001213867,0.0002670968,0.2966031,0.001457285,0.5000557,0.01145207,0.1878686],"study_design_scores_gemma":[0.00006683954,0.00007159984,0.0001024382,0.00002553526,0.00001072762,0.0000299205,0.00004156087,0.6507961,0.0007758049,0.3411627,0.006901978,0.00001491284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007567671,0.0002728354,0.9844,0.00150111,0.0001746919,0.00003034738,0.00002658307,0.0004630105,0.005563701],"genre_scores_gemma":[0.5051724,0.0005541239,0.4817035,0.002075983,0.0002951511,0.0002175969,0.0001241385,0.0002943475,0.009562753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00582947,"threshold_uncertainty_score":0.01950157,"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."}}