{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00168209,0.0007712957,0.0009844758,0.0003916027,0.000351914,0.0007771545,0.001195873,0.0008270646,0.001647876],"category_scores_gemma":[0.003388572,0.0003719297,0.0004747928,0.0003152701,0.001263592,0.0009958716,0.001112139,0.001247937,0.000168308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001445127,"about_ca_system_score_gemma":0.001175369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005129432,"about_ca_topic_score_gemma":0.003683539,"domain_scores_codex":[0.9991304,0.00032576,0.00004077781,0.0001809534,0.0002100853,0.0001119951],"domain_scores_gemma":[0.9987388,0.0007799153,0.0001521758,0.00006322841,0.0001445813,0.0001213876],"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":[0.00009461135,0.00006732555,0.000470863,0.00004833722,0.00003040864,0.00009520592,0.00008734595,0.9463673,0.001640662,0.03420153,0.0003424014,0.01655404],"study_design_scores_gemma":[0.00001391474,0.00002756212,0.00004319271,0.000001843491,0.000004162746,0.000005973685,0.000002538198,0.9956191,0.0001548185,0.003985118,0.0001385598,0.000003201917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03792588,0.0001452079,0.9583173,0.000161129,0.00002886542,0.00006839058,0.0000245279,0.0001623439,0.003166328],"genre_scores_gemma":[0.9409469,0.00009733241,0.05653296,0.00005878576,0.00001832037,0.0001097181,0.0000218759,0.00001647844,0.002197754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005129432,"threshold_uncertainty_score":0.01048517,"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."}}