{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001493703,0.0009039427,0.0005941081,0.000528355,0.0003226219,0.0008603788,0.001480202,0.00107149,0.004367696],"category_scores_gemma":[0.01388547,0.0003468184,0.0005164714,0.0005853419,0.000937224,0.001889586,0.00095783,0.001494654,0.0004676837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000682091,"about_ca_system_score_gemma":0.000947124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003981332,"about_ca_topic_score_gemma":0.004277646,"domain_scores_codex":[0.9992456,0.0003520468,0.00004480791,0.0001503217,0.0001302356,0.00007700443],"domain_scores_gemma":[0.9911911,0.00715922,0.0007911923,0.0004172158,0.0002781089,0.00016309],"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":[0.0003268296,0.0004483424,0.0033771,0.000219386,0.00008160874,0.0001155575,0.0001489169,0.9166353,0.00166735,0.01441044,0.001717438,0.06085176],"study_design_scores_gemma":[0.00005221783,0.00006067533,0.0002229796,0.000006884473,0.000004716968,0.00001552908,0.00002243632,0.9907155,0.000654756,0.007792353,0.0004477228,0.000004200843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6030672,0.0009007857,0.3796929,0.001235606,0.0001321256,0.000272196,0.0002863352,0.0008758135,0.01353706],"genre_scores_gemma":[0.8614694,0.0003147669,0.1341774,0.0001420637,0.00002668132,0.0001819533,0.000355571,0.00009169646,0.003240302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004367696,"threshold_uncertainty_score":0.01461142,"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."}}