{"id":"W1597317312","doi":"10.1007/978-3-540-75538-8_11","title":"Feature Construction for Reinforcement Learning in Hearts","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Temporal difference learning; Artificial intelligence; Variety (cybernetics); Set (abstract data type); Representation (politics); Monte Carlo tree search; Machine learning; Mathematics","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":[0.0007397069,0.0003036967,0.0005819651,0.0002850623,0.0003700947,0.0007387703,0.00117215,0.0006899619,0.007835563],"category_scores_gemma":[0.002849931,0.0002481849,0.0004855856,0.0002739206,0.0008181523,0.001583498,0.001350366,0.001356737,0.0007151493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006459607,"about_ca_system_score_gemma":0.0003859127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001132057,"about_ca_topic_score_gemma":0.00142976,"domain_scores_codex":[0.9997244,0.00008720357,0.00001739677,0.00007312821,0.00005715226,0.00004063821],"domain_scores_gemma":[0.9992824,0.0004653962,0.00003090673,0.00009978023,0.00007655963,0.00004500451],"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":[0.0002270868,0.0001030819,0.0009225704,0.0001658039,0.00003503419,0.0001016146,0.0002324208,0.1768536,0.006300105,0.3355577,0.0062522,0.4732489],"study_design_scores_gemma":[0.00002862994,0.0000507419,0.000192694,0.00002150515,0.000009448077,0.00003426179,0.00002144633,0.7840031,0.00192595,0.2110508,0.002651116,0.00001023067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01063268,0.000102291,0.9852989,0.00009194667,0.00003660471,0.0000236242,0.00003211506,0.0003980334,0.003383881],"genre_scores_gemma":[0.5572715,0.0001563428,0.4340591,0.00007467804,0.00005406516,0.0001756248,0.000185252,0.0002383551,0.007785164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007835563,"threshold_uncertainty_score":0.02621257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0341011876407591,"score_gpt":0.2915072131869799,"score_spread":0.2574060255462208,"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."}}