{"id":"W4318604500","doi":"10.1109/ssci51031.2022.10022098","title":"Hierarchical Reinforcement Learning With Multi Discount Factors In A Differential Game","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Guidance and Control Systems","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Differential game; Differential (mechanical device); Function (biology); Path (computing); Artificial intelligence; Mathematical optimization; Mathematics; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001497811,0.0002918204,0.0003032078,0.0002328886,0.0002471385,0.00009050236,0.0003074947,0.00004411071,0.0003122299],"category_scores_gemma":[0.000008622366,0.0002705542,0.00008601762,0.0003833238,0.00007557214,0.000208796,0.00007311022,0.0006492084,0.0000278604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003562066,"about_ca_system_score_gemma":0.00006144073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009116557,"about_ca_topic_score_gemma":0.00009644809,"domain_scores_codex":[0.9979038,0.0001111789,0.0004801318,0.0003620489,0.0007400528,0.0004028274],"domain_scores_gemma":[0.999476,0.000136034,0.00008073201,0.0001696967,0.00004329002,0.00009430994],"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":[0.0001663933,0.00007337968,0.001773822,0.00003389381,0.0000542633,0.00002524268,0.002283572,0.9910957,0.00196874,0.002206726,0.00005103586,0.0002672538],"study_design_scores_gemma":[0.0003847276,0.0007442993,0.00245847,0.00005036862,0.00001140813,0.00002207475,0.002000568,0.9908683,0.001298335,0.0002440579,0.00148837,0.0004290519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7692184,0.00006719225,0.2274575,0.0002728476,0.001323543,0.0005844795,0.00003248483,0.00025849,0.0007850709],"genre_scores_gemma":[0.9985194,0.0000211185,0.0001381738,0.00005702173,0.00009271336,0.0002662203,0.0001175716,0.00004551563,0.0007422569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.229301,"threshold_uncertainty_score":0.9999747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01383266406375146,"score_gpt":0.2298687803865991,"score_spread":0.2160361163228476,"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."}}