{"id":"W2949784712","doi":"10.48550/arxiv.1906.04477","title":"Causal Discovery with Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Cognitive science; Psychology; Artificial intelligence; Social psychology","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":[0.005972693,0.001572454,0.002494255,0.001999927,0.0008658927,0.001698615,0.00302616,0.00197096,0.004914888],"category_scores_gemma":[0.02926814,0.001009288,0.001192588,0.001834196,0.00217688,0.002570548,0.002446656,0.003349656,0.0007052241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0020977,"about_ca_system_score_gemma":0.00277918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006600603,"about_ca_topic_score_gemma":0.00803776,"domain_scores_codex":[0.9964729,0.001985632,0.0001536564,0.000732021,0.0004783625,0.0001773557],"domain_scores_gemma":[0.9793602,0.01729178,0.0009534584,0.00124142,0.0007588755,0.0003942333],"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":[0.0001463665,0.0001259967,0.002532356,0.0002026311,0.0001657845,0.0001459584,0.00009711865,0.8491279,0.0003342353,0.07188345,0.002701913,0.07253623],"study_design_scores_gemma":[0.00003029419,0.00001200871,0.00006649304,0.0000102327,0.00001108815,0.00001389023,0.000004377385,0.9472975,0.0001251022,0.05203318,0.000389935,0.00000588686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008382028,0.0004023074,0.98796,0.0006359472,0.00004901126,0.00008548661,0.0001697502,0.0006447015,0.001670802],"genre_scores_gemma":[0.6392045,0.0005407383,0.3548102,0.000594893,0.0001930775,0.0005738811,0.0007176019,0.0001983634,0.003166768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006600603,"threshold_uncertainty_score":0.031587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05887176603568913,"score_gpt":0.1842319754472586,"score_spread":0.1253602094115694,"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."}}