{"id":"W4200555244","doi":"10.11606/t.55.2021.tde-21122021-111842","title":"Synthesizing interpretable strategies for real-time planning in zero-sum games","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Mathematical Sciences; Centro de Ciências Matemáticas Aplicadas à Indústria; Universidade Federal de Viçosa; Fundação de Amparo à Pesquisa do Estado de São Paulo; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Compute Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Computer science; Scripting language; Action (physics); Artificial intelligence; Set (abstract data type); Abstraction; Zero (linguistics); Machine learning; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003486012,0.000318111,0.0004735432,0.0002939418,0.000093913,0.0009287599,0.0009396122,0.0002562189,0.00006639372],"category_scores_gemma":[0.0001708682,0.0003240448,0.0001301882,0.0002944563,0.00001327762,0.0007730975,0.0001137179,0.0003054372,0.00002961518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009912477,"about_ca_system_score_gemma":0.0004430418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001038689,"about_ca_topic_score_gemma":0.0000344077,"domain_scores_codex":[0.9980457,0.00006222813,0.0005242599,0.0005942556,0.000307971,0.0004655746],"domain_scores_gemma":[0.9985001,0.0004963458,0.0002763984,0.0005392791,0.0001339619,0.00005390869],"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":[0.00005731072,0.00004484781,0.0002060078,0.001006875,0.0001537017,0.00007231565,0.01416276,0.8971233,0.00759434,0.06896999,0.004453289,0.006155276],"study_design_scores_gemma":[0.0002879251,0.0001236784,0.0003471871,0.002306365,0.00003100407,0.000004857222,0.006794218,0.982015,0.003819223,0.002046711,0.001477907,0.0007458946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003710655,0.0001907485,0.8610263,0.000034514,0.0007264782,0.0003634415,0.000001407077,0.0002635556,0.1336829],"genre_scores_gemma":[0.3120044,0.000228822,0.3979104,0.0002215286,0.0002169327,0.0003875142,0.001299261,0.0002006238,0.2875305],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4631158,"threshold_uncertainty_score":0.9999211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819622761745324,"score_gpt":0.2910867091637649,"score_spread":0.2728904815463116,"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."}}