{"id":"W2954089099","doi":"10.1145/3321707.3321866","title":"Evolving dota 2 shadow fiend bots using genetic programming with external memory","year":2019,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Heuristics; Observability; Context (archaeology); Genetic programming; Shadow (psychology); Artificial intelligence; Reinforcement learning; Set (abstract data type); Task (project management); Human–computer interaction; Programming language; Psychology; Engineering; 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":[0.000134593,0.0001752064,0.0001798109,0.00009482752,0.0002058047,0.0001946743,0.0006726772,0.00005483499,0.00001927847],"category_scores_gemma":[0.00003351363,0.0001359099,0.00004447216,0.0003419462,0.000207875,0.000469808,0.0003861367,0.000131181,0.000007812139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004822508,"about_ca_system_score_gemma":0.0001523361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008113892,"about_ca_topic_score_gemma":0.000002031442,"domain_scores_codex":[0.9985,0.00001698965,0.0003327492,0.0004400417,0.0004371612,0.0002730726],"domain_scores_gemma":[0.9988251,0.00006218444,0.0003019591,0.0001499575,0.0005856453,0.00007512993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000105658,0.0002560173,0.4751687,0.0006309292,0.0001214497,0.000006513786,0.008321808,0.123779,0.04259581,0.02187712,0.0003375297,0.3267995],"study_design_scores_gemma":[0.0001344462,0.0001416008,0.1611971,0.0002642582,0.00001802332,0.0001392278,0.0003545954,0.8221235,0.001874522,0.01351005,0.0000320456,0.0002105972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6962656,0.0004343234,0.3021561,0.0001971548,0.0001690722,0.0003417392,7.389357e-7,0.00004459967,0.0003907057],"genre_scores_gemma":[0.7316492,0.00001151966,0.2681671,0.00003920119,0.00003602049,0.000007399337,1.89548e-7,0.000007854241,0.00008143851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6983445,"threshold_uncertainty_score":0.5542245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0237815563799038,"score_gpt":0.2475599406890724,"score_spread":0.2237783843091686,"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."}}