{"id":"W4311072863","doi":"10.1613/jair.1.13769","title":"Asymmetric Action Abstractions for Planning in Real-Time Strategy Games","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; University of Alberta; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Universidade Federal de Viçosa; Canadian Institute for Advanced Research","keywords":"Computer science; Iterative deepening depth-first search; Action (physics); Search algorithm; Set (abstract data type); Context (archaeology); Theoretical computer science; Greedy algorithm; Combinatorial game theory; Tree (set theory); Abstraction; Search tree; Sequential game; Beam search; Game theory; Algorithm; Best-first search; Mathematics; Mathematical economics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.008409568,0.000168039,0.0003454117,0.002694893,0.0007395977,0.0004048679,0.001824102,0.00009260787,0.0002486211],"category_scores_gemma":[0.001237674,0.0001712079,0.0002070598,0.003166809,0.0001685706,0.001115675,0.0003500925,0.001479012,0.0001031351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000706525,"about_ca_system_score_gemma":0.0007808444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002541284,"about_ca_topic_score_gemma":0.00004906385,"domain_scores_codex":[0.9952219,0.0006281779,0.001347216,0.0004122528,0.001597595,0.000792924],"domain_scores_gemma":[0.9952483,0.002638728,0.0004883106,0.0004165303,0.001011314,0.0001968371],"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":[0.0003507275,0.0007060769,0.0002232841,0.00002093321,0.00004014539,0.0001866812,0.002660311,0.2041996,0.0279524,0.0412644,0.002306624,0.7200888],"study_design_scores_gemma":[0.00009853886,0.003791644,0.0009450343,0.00009787666,0.00001230714,0.0003454202,0.02498538,0.4772572,0.166586,0.3155801,0.009752139,0.000548347],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3490779,0.0007269988,0.6400734,0.003049661,0.002073111,0.00105414,0.0000120133,0.00009857028,0.003834284],"genre_scores_gemma":[0.9891623,0.0002426445,0.009776947,0.00002292225,0.0004137587,0.00007568952,0.000001663893,0.00002288321,0.0002811395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7195405,"threshold_uncertainty_score":0.6981655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.333043060617828,"score_gpt":0.4888081539774601,"score_spread":0.1557650933596322,"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."}}