{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001517561,0.0005852384,0.0009276567,0.0002980204,0.000331164,0.001046089,0.001171332,0.001141574,0.002936218],"category_scores_gemma":[0.005098369,0.0004119865,0.0005088639,0.0002954866,0.00136509,0.001449177,0.001078232,0.001873557,0.0002780808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00135264,"about_ca_system_score_gemma":0.001267784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005092747,"about_ca_topic_score_gemma":0.00488189,"domain_scores_codex":[0.9995868,0.0001692975,0.0000195466,0.0000758126,0.00007517873,0.00007343799],"domain_scores_gemma":[0.9982835,0.001176333,0.0001838384,0.00009477678,0.0001503714,0.000111079],"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":[0.00001683456,0.00001939356,0.0003175025,0.00002225258,0.00001436828,0.00003207154,0.00002902646,0.9659448,0.000361706,0.02789292,0.0002763259,0.005072918],"study_design_scores_gemma":[0.000003597528,0.000005434945,0.00002775259,0.000002258454,0.000001318425,0.000002733897,0.000001750562,0.9904288,0.00008955836,0.00933496,0.00010006,0.000001700286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05419444,0.000295526,0.9394695,0.0009073424,0.0000672417,0.00003410573,0.00006353131,0.0003288051,0.004639547],"genre_scores_gemma":[0.915987,0.0002026272,0.07947106,0.0002014646,0.00004182003,0.00008275969,0.00006169893,0.0000601612,0.0038913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005092747,"threshold_uncertainty_score":0.01012617,"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."}}