{"id":"W1552645109","doi":"10.1184/r1/6558128","title":"Plays as Effective Multiagent Plans Enabling Opponent-Adaptive Play Selection","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"U.S. Air Force","keywords":"Computer science; Adversarial system; Adversary; Robot; Set (abstract data type); Adaptation (eye); Domain (mathematical analysis); Focus (optics); Plan (archaeology); Artificial intelligence; Human–computer interaction; Selection (genetic algorithm); Multi-agent system; Computer security","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007026222,0.0006253327,0.0002896871,0.0003759835,0.0003624759,0.0008419577,0.0009847606,0.0005805502,0.003841846],"category_scores_gemma":[0.002254399,0.0003843375,0.0003557183,0.0002153242,0.001344866,0.001146767,0.001633045,0.00106803,0.0006020858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004586846,"about_ca_system_score_gemma":0.0005465858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001076439,"about_ca_topic_score_gemma":0.001846165,"domain_scores_codex":[0.9996284,0.0001333261,0.00001802882,0.00006273125,0.0001129701,0.00004451435],"domain_scores_gemma":[0.9992462,0.00034188,0.0001110701,0.0001248882,0.00007387383,0.0001021554],"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":[0.0003982269,0.0002057437,0.002023258,0.0001515348,0.00007899174,0.0005475981,0.0006536419,0.6538045,0.02283052,0.1871555,0.005074735,0.1270757],"study_design_scores_gemma":[0.00004276368,0.000123876,0.0003803838,0.00001980539,0.00001748773,0.00007693493,0.00008012321,0.9278764,0.00459255,0.06068295,0.006091495,0.00001524751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04347392,0.0001853247,0.9459595,0.0002270338,0.00006853908,0.0001638566,0.00009144067,0.001545358,0.008285025],"genre_scores_gemma":[0.7453131,0.0001794429,0.2471673,0.0001323243,0.00003202349,0.0002988401,0.0001581962,0.0001855773,0.006533203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003841846,"threshold_uncertainty_score":0.01285225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03495788689315934,"score_gpt":0.2723060358484843,"score_spread":0.237348148955325,"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."}}