{"id":"W4402007577","doi":"10.1007/978-3-031-70893-0_2","title":"Efficiently Training Neural Networks for Imperfect Information Games by Sampling Information Sets","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Perfect information; Artificial neural network; Training (meteorology); Imperfect; Artificial intelligence; Sampling (signal processing); Machine learning; Computer vision; Mathematics; Mathematical economics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001246777,0.0005636968,0.0004728872,0.0009883838,0.0003665332,0.002452417,0.002408497,0.0003892721,0.000008764109],"category_scores_gemma":[0.000236234,0.0005223014,0.0002036619,0.0007337032,0.0004269344,0.004155609,0.0007952728,0.0008484066,0.0000652438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003393166,"about_ca_system_score_gemma":0.0003082488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002176623,"about_ca_topic_score_gemma":0.00001856471,"domain_scores_codex":[0.9964742,0.00001891191,0.001005258,0.0007763144,0.0008585621,0.0008667197],"domain_scores_gemma":[0.9973661,0.0008808618,0.0004266665,0.000788853,0.0003729725,0.0001645846],"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":[0.000004676347,0.000003185619,0.000002461568,0.00004441462,0.000006024374,0.00000125874,0.002908873,0.3534393,0.000008773327,0.006756889,0.00009221995,0.6367319],"study_design_scores_gemma":[0.00008075863,0.0001720587,0.000004308557,0.0002665941,0.000009089189,0.00003031053,0.000003439773,0.9486049,0.0003852281,0.0400179,0.009886372,0.0005390659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001824226,0.0004299878,0.9922567,0.0006164184,0.004362567,0.0008449947,0.00003953762,0.0003609664,0.0009064114],"genre_scores_gemma":[0.6294963,0.0000678611,0.3640642,0.004912417,0.000913885,0.0001107765,0.000200739,0.00007085114,0.0001629669],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6361928,"threshold_uncertainty_score":0.9997228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02881157661154738,"score_gpt":0.2810092525429389,"score_spread":0.2521976759313915,"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."}}