{"id":"W4407870583","doi":"10.3390/risks13030040","title":"Deep Reinforcement Learning in Non-Markov Market-Making","year":2025,"lang":"en","type":"article","venue":"Risks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Reinforcement learning; Artificial intelligence; Markov chain; Reinforcement; Computer science; Economics; Machine learning; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006992958,0.0001772563,0.0002072018,0.0003620735,0.0001681233,0.0002072263,0.0008918276,0.00009555964,0.00008601549],"category_scores_gemma":[0.0003001906,0.0001850932,0.00006795049,0.0007939763,0.00003118911,0.0003393969,0.0006043476,0.0004991191,0.00007550386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000193485,"about_ca_system_score_gemma":0.00008426786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006020938,"about_ca_topic_score_gemma":0.0000128142,"domain_scores_codex":[0.9983227,0.0001011402,0.0004155654,0.0003745089,0.0003179505,0.000468111],"domain_scores_gemma":[0.9989645,0.0002419576,0.0001428337,0.000552358,0.00005258721,0.00004577043],"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":[0.000007835582,0.000008691246,0.01398549,0.00003036199,0.00001591951,0.00001757149,0.0003823989,0.9497623,0.00002449804,0.004030806,0.0006361229,0.03109801],"study_design_scores_gemma":[0.0003738822,0.00004620202,0.02038813,0.0001780556,0.000005418413,0.000001520789,0.00006094736,0.9712558,0.00007499608,0.0002032977,0.007232914,0.0001788834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008516671,0.00006819561,0.8406162,0.0002873287,0.0003900426,0.0001909487,1.488977e-8,0.0001469618,0.1574487],"genre_scores_gemma":[0.9724175,0.00004521057,0.01778784,0.0004578778,0.00002923014,0.00002326336,0.0000015275,0.00001015042,0.009227424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9715658,"threshold_uncertainty_score":0.7547884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01654078273632921,"score_gpt":0.2945006458921195,"score_spread":0.2779598631557903,"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."}}