{"id":"W4406209209","doi":"10.2139/ssrn.5024095","title":"Reinforcement Learning in Non-Markov Market-Making","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Mathematical optimization; Maximization; Artificial intelligence; Limit (mathematics); Markov process; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003480919,0.0008181288,0.002330301,0.0005862061,0.0008029554,0.002279656,0.002076348,0.002666736,0.008324804],"category_scores_gemma":[0.01822014,0.0008290491,0.000911669,0.0007184559,0.002831975,0.003644629,0.001824554,0.002647432,0.0004857398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001943569,"about_ca_system_score_gemma":0.00163788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007416334,"about_ca_topic_score_gemma":0.005258931,"domain_scores_codex":[0.998575,0.0008173368,0.00006334628,0.0002061355,0.0001491978,0.0001890201],"domain_scores_gemma":[0.9822921,0.01543227,0.0007498315,0.0003336526,0.0005009921,0.0006913227],"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":[0.000232343,0.0001377746,0.00110126,0.0001361452,0.00009491388,0.0001609004,0.0001243978,0.6501252,0.0004673014,0.3343377,0.001825784,0.01125618],"study_design_scores_gemma":[0.00004577897,0.00002514701,0.0001032175,0.000007112134,0.000008556231,0.00001067852,0.00001303878,0.8440552,0.0000578755,0.1554614,0.0002022949,0.000009694684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1984356,0.001077754,0.7786125,0.003464508,0.0002509595,0.0001093689,0.0002677358,0.0003040743,0.01747748],"genre_scores_gemma":[0.9647666,0.0005276936,0.02212258,0.0001976901,0.0001160607,0.0001357755,0.0001095903,0.00005282603,0.01197113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008324804,"threshold_uncertainty_score":0.02784926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008008819207830534,"score_gpt":0.2608087152248799,"score_spread":0.2527998960170494,"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."}}