{"id":"W4402353118","doi":"10.1109/cisce62493.2024.10653102","title":"Exploration of the Possibility for a Wider Range of the Discount Factor for Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Reinforcement; Range (aeronautics); Computer science; Factor (programming language); Artificial intelligence; Machine learning; Psychology; Engineering; Social psychology; Aerospace engineering; Programming language","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":[0.008900735,0.001571295,0.0012122,0.0008873893,0.0005688043,0.002901633,0.002315858,0.001538962,0.002373853],"category_scores_gemma":[0.05546004,0.0007810616,0.0009434812,0.0007167585,0.001735225,0.006587181,0.002143907,0.004504981,0.000314429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001525302,"about_ca_system_score_gemma":0.001503125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002502905,"about_ca_topic_score_gemma":0.002747723,"domain_scores_codex":[0.9968877,0.001510499,0.0002146968,0.0007596784,0.0004048094,0.0002225151],"domain_scores_gemma":[0.9532889,0.03935619,0.00198864,0.003091471,0.001223181,0.001051559],"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":[0.001693129,0.0009313079,0.009369234,0.0009450649,0.000334312,0.0004455341,0.0008564805,0.6807818,0.01213133,0.1360342,0.002065797,0.1544118],"study_design_scores_gemma":[0.000298273,0.00092659,0.001687642,0.000397118,0.0001450804,0.0002730706,0.0002069279,0.8456407,0.005031927,0.1398934,0.005367829,0.0001315688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2005872,0.00498553,0.7761354,0.002516726,0.000224418,0.0002660854,0.0001861617,0.0007210397,0.01437736],"genre_scores_gemma":[0.8898701,0.0009605762,0.1079733,0.000264305,0.00005342599,0.0001534606,0.00005746342,0.00009744123,0.0005698715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008900735,"threshold_uncertainty_score":0.04707211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0494761660167853,"score_gpt":0.2979828257252523,"score_spread":0.248506659708467,"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."}}