{"id":"W2394492371","doi":"","title":"Solving nonogram puzzles by reinforcement learning","year":2012,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Solver; Connectionism; Computer science; Heuristic; Constraint satisfaction problem; Artificial intelligence; Temporal difference learning; Artificial neural network; Programming language","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0003628527,0.0003437103,0.0002508308,0.0001601442,0.0003334169,0.003153365,0.001460623,0.0001469557,0.0003287124],"category_scores_gemma":[0.0003655892,0.0003250139,0.0001732493,0.0005922174,0.0001121568,0.01617036,0.0009656033,0.0006046618,0.006417928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005292119,"about_ca_system_score_gemma":0.00006032113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003914814,"about_ca_topic_score_gemma":2.367212e-7,"domain_scores_codex":[0.9972731,0.00009289962,0.0005732091,0.0004680266,0.0005482665,0.001044461],"domain_scores_gemma":[0.9983895,0.0002404839,0.0001982744,0.0005930373,0.00004058366,0.000538055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005084114,0.0006472607,0.5865797,0.00008218228,0.0001264742,0.00002942046,0.001040987,0.001045051,0.001666725,0.06567168,0.04421363,0.298846],"study_design_scores_gemma":[0.0001295296,0.0001078687,0.0006927354,0.00007612227,0.000008499716,0.00001800216,0.0001237263,0.009646732,0.03678362,0.005463095,0.9461424,0.0008076964],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2153457,0.002283106,0.6341684,0.002355636,0.001314734,0.0007973991,0.0001494413,0.003879545,0.1397061],"genre_scores_gemma":[0.9886801,0.00002732679,0.006703007,0.0006784399,0.0002361148,0.00002884147,0.0001287807,0.00005593445,0.003461414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9019287,"threshold_uncertainty_score":0.9999202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02060443729135078,"score_gpt":0.2382299284476171,"score_spread":0.2176254911562664,"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."}}