{"id":"W3047624789","doi":"10.1109/aim43001.2020.9158960","title":"A Reinforcement Learning Based Multiple Strategy Framework for Tracking a Moving Target","year":2020,"lang":"en","type":"article","venue":"","topic":"Guidance and Control Systems","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Reinforcement learning; Pursuer; Computer science; Artificial intelligence; Motion planning; Complementarity (molecular biology); Mobile robot; Robotics; Motion (physics); Machine learning; Robot; Mathematical optimization; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009565781,0.0001332147,0.0001829998,0.00002405984,0.0000688334,0.0000702329,0.00009693797,0.00007536588,0.0001091131],"category_scores_gemma":[0.0001533021,0.0001301005,0.00008850727,0.00009540762,0.000004532369,0.0001085563,0.00000796252,0.0001697404,0.00002646886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002836133,"about_ca_system_score_gemma":0.00001604487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001583166,"about_ca_topic_score_gemma":0.000004444548,"domain_scores_codex":[0.9992095,0.00001125703,0.0002409645,0.0001472594,0.0001111593,0.0002798815],"domain_scores_gemma":[0.9996164,0.0001404759,0.00003079514,0.00008889046,0.00003042618,0.00009298165],"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":[0.00001657616,0.000002639964,0.0007149716,0.000119598,0.00002568389,0.000001693052,0.0002592305,0.9904091,0.005412561,0.0008753681,0.0002550199,0.001907532],"study_design_scores_gemma":[0.0005744004,0.00008289983,0.00007516699,0.00005058529,0.000006954762,2.291288e-7,0.0004129084,0.9857742,0.003439284,0.00009917105,0.009319326,0.0001648692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005425777,0.0001705457,0.9910771,0.0002067115,0.0001023793,0.0003485243,0.000001489378,0.0005486069,0.002118823],"genre_scores_gemma":[0.9852318,0.000001776935,0.01390422,0.0004186289,0.0002150687,0.0001115799,0.000009207153,0.00003665879,0.00007112052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9798059,"threshold_uncertainty_score":0.5305345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0250636834815028,"score_gpt":0.2300082399309999,"score_spread":0.2049445564494971,"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."}}