{"id":"W7102329548","doi":"","title":"Causal Deep Q Network","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Spurious relationship; Reinforcement learning; Causal model; Causal reasoning; Benchmark (surveying); Associative property; Causal structure","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001263417,0.0006189478,0.0005998739,0.0006057947,0.000498111,0.0008344631,0.001573344,0.001061491,0.005425085],"category_scores_gemma":[0.005691177,0.0003946379,0.0004990962,0.0006003524,0.001230886,0.001586531,0.001396127,0.00141056,0.000515428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001060291,"about_ca_system_score_gemma":0.001471614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005443381,"about_ca_topic_score_gemma":0.00753776,"domain_scores_codex":[0.9994922,0.000170781,0.00002668917,0.000143525,0.0001123582,0.00005450399],"domain_scores_gemma":[0.9982693,0.0009337052,0.0001850144,0.0001704541,0.0003252143,0.0001162589],"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":[0.0001272523,0.00009605029,0.002613422,0.0001856081,0.00009063624,0.000169326,0.00009551401,0.710234,0.002708148,0.1402364,0.004275281,0.1391683],"study_design_scores_gemma":[0.0000111613,0.00002184239,0.0001435401,0.00001223566,0.00001279913,0.0000210695,0.000007903098,0.9357034,0.0005498728,0.06169505,0.001815215,0.000005808747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01265999,0.0003475066,0.9808385,0.0005562886,0.00007758108,0.00004957599,0.0001719548,0.0005763152,0.004722178],"genre_scores_gemma":[0.7522476,0.0007391438,0.2392414,0.0005551792,0.0001042653,0.0001848908,0.000418084,0.0001161732,0.006393292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005443381,"threshold_uncertainty_score":0.01814878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02682050421823448,"score_gpt":0.2705352088287046,"score_spread":0.2437147046104702,"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."}}