{"id":"W4410117844","doi":"10.1080/1350486x.2026.2662658","title":"Multi-Agent Reinforcement Learning for Greenhouse Gas Offset Credit Markets","year":2025,"lang":"en","type":"preprint","venue":"Applied Mathematical Finance","topic":"Banking stability, regulation, efficiency","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Offset (computer science); Reinforcement learning; Greenhouse gas; Reinforcement; Business; Environmental science; Natural resource economics; Monetary economics; Economics; Computer science; Materials science; Artificial intelligence; Geology; Composite material; Operating system","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001612433,0.0005263775,0.001162038,0.0002606791,0.0002614627,0.0001535727,0.0007635874,0.0005157365,0.0003400016],"category_scores_gemma":[0.0008027597,0.000620865,0.0003612656,0.0002594297,0.000162722,0.00006527155,0.0007531277,0.0006657357,0.0003460486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003651348,"about_ca_system_score_gemma":0.00009967174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001361731,"about_ca_topic_score_gemma":0.000003179549,"domain_scores_codex":[0.9961516,0.00002110045,0.001731205,0.001305776,0.0001429962,0.0006473058],"domain_scores_gemma":[0.997078,0.000473405,0.0009973483,0.001268158,0.0001032859,0.00007979698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000610702,0.0004772056,0.0003252461,0.002477161,0.00008688404,0.00000102668,0.000707644,0.03437458,0.000006922351,0.9551911,0.001751911,0.004539189],"study_design_scores_gemma":[0.001154744,0.00006359011,0.002311955,0.0004232431,0.00004703919,0.000001340754,0.00002780072,0.3442041,0.00009705547,0.6136159,0.03718427,0.000868936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03058816,0.00111872,0.9363882,0.0004165772,0.0007726711,0.00341331,0.0002626712,0.0002604176,0.02677928],"genre_scores_gemma":[0.8965199,0.0004296907,0.09260462,0.0001144989,0.0001997614,0.001945933,0.0001945182,0.00009031031,0.007900752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8659317,"threshold_uncertainty_score":0.9996243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03512460389985603,"score_gpt":0.2572911741154643,"score_spread":0.2221665702156083,"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."}}