{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001439699,0.001456256,0.0007055858,0.0006102209,0.0005023937,0.001635679,0.00138996,0.0009391073,0.004040234],"category_scores_gemma":[0.007267307,0.0005311171,0.001466998,0.0003567349,0.002319347,0.001700188,0.001885105,0.001837605,0.0007383779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001607844,"about_ca_system_score_gemma":0.002069668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003796235,"about_ca_topic_score_gemma":0.008800021,"domain_scores_codex":[0.9988413,0.0003605699,0.0001031775,0.0002476096,0.0003376504,0.0001095487],"domain_scores_gemma":[0.9975068,0.001682136,0.0001856156,0.0002709229,0.0002362577,0.000118214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002225964,0.0002091918,0.001726244,0.0004587782,0.00007658572,0.0004663955,0.001130514,0.7301843,0.01031221,0.1456876,0.003143587,0.1063821],"study_design_scores_gemma":[0.00005678022,0.00007603019,0.0001337071,0.00005021193,0.00003153987,0.0000451968,0.0001236471,0.9110696,0.006438081,0.07698185,0.004974873,0.00001847028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04878865,0.0002432528,0.9389384,0.0005783794,0.00008999609,0.000327651,0.0002902113,0.002972971,0.007770432],"genre_scores_gemma":[0.4210334,0.0003084183,0.5718736,0.000307116,0.00002654963,0.0005653104,0.0008185817,0.0006972448,0.004369764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004040234,"threshold_uncertainty_score":0.01351595,"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."}}