{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001407354,0.0004352846,0.0004538896,0.001164803,0.000251774,0.000400707,0.00172922,0.0004276131,0.0000135789],"category_scores_gemma":[0.0002224766,0.0004300966,0.0001292417,0.0006422729,0.0006731605,0.0005862925,0.000636081,0.001092623,0.00002685477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004947063,"about_ca_system_score_gemma":0.0004421637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002753708,"about_ca_topic_score_gemma":0.0002363127,"domain_scores_codex":[0.9965713,0.00002457926,0.0005329864,0.001290619,0.0007940667,0.0007864736],"domain_scores_gemma":[0.9978877,0.0006435208,0.0002986757,0.0007663268,0.0002737804,0.0001300438],"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":[0.00001030015,0.000007813913,0.0001152835,0.00002455882,0.000003770024,0.00003073263,0.0006819615,0.2382427,0.00006673779,0.03739477,0.00002710475,0.7233943],"study_design_scores_gemma":[0.0001571412,0.0002846573,0.00004759661,0.0004710466,0.000004025106,0.00007582614,0.000001232031,0.856343,0.005491077,0.122269,0.01420486,0.0006504873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006312574,0.0002289985,0.9924549,0.001345806,0.002216947,0.0006982391,7.936713e-7,0.0001490753,0.002842134],"genre_scores_gemma":[0.08630309,0.00005660359,0.909653,0.001503527,0.0007408215,0.00002740957,0.000007920569,0.00004599806,0.001661644],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7227438,"threshold_uncertainty_score":0.9998151,"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."}}