{"id":"W2902955471","doi":"10.1609/aiide.v14i1.13018","title":"Action Abstractions for Combinatorial Multi-Armed Bandit Tree Search","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; University of Alberta","keywords":"Action (physics); Computer science; Abstraction; Space (punctuation); Tree (set theory); State (computer science); Theoretical computer science; Machine learning; Algorithm; Mathematics","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":[0.0002942763,0.0002967546,0.0002853388,0.0001562189,0.0003704671,0.0008022245,0.001094379,0.000102596,0.00005424338],"category_scores_gemma":[0.000422455,0.0002302571,0.0001879758,0.0002712545,0.0006161443,0.001697058,0.0003916107,0.0002928652,0.000102228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001531793,"about_ca_system_score_gemma":0.00007390417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003825879,"about_ca_topic_score_gemma":0.00002390157,"domain_scores_codex":[0.9978036,0.00001690568,0.0006336162,0.0006442242,0.0004646117,0.0004370211],"domain_scores_gemma":[0.997883,0.0002673517,0.0003560494,0.0002673683,0.001089234,0.0001369647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007641694,0.001185481,0.0004805485,0.00005046837,0.000119978,6.105454e-7,0.005489608,0.00001785519,0.04256353,0.5422067,0.0003606098,0.4067605],"study_design_scores_gemma":[0.000102867,0.001399447,0.0003498084,0.0001940715,0.00001769748,0.000007253063,0.005001618,0.06099608,0.8682368,0.06253618,0.0008563116,0.0003018418],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6569259,0.00001821346,0.3159839,0.004893372,0.004450105,0.002336824,0.00007000299,0.0001916332,0.01513003],"genre_scores_gemma":[0.9981813,0.00002396587,0.00089937,0.0001421071,0.0002288891,0.00009729247,0.00000247182,0.00001749348,0.0004070518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8256733,"threshold_uncertainty_score":0.9389612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1163859848837063,"score_gpt":0.3538952261254863,"score_spread":0.23750924124178,"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."}}