{"id":"W3206265976","doi":"10.48550/arxiv.2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based\\n Reinforcement Learning","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Causality (physics); Causal model; Causal structure; Reinforcement learning; Premise; Computer science; Modularity (biology); Artificial intelligence; Machine learning; Causal reasoning; Representation (politics); Psychology; Mathematics; Cognition","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005045834,0.0005074842,0.0009267081,0.0007633996,0.0002125426,0.0003660384,0.001334294,0.0003681491,0.00005801074],"category_scores_gemma":[0.0009543617,0.0006096404,0.0003197442,0.001409593,0.0001231232,0.001502488,0.001401503,0.001159186,0.00002370014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054331,"about_ca_system_score_gemma":0.002116486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006244805,"about_ca_topic_score_gemma":0.0001699294,"domain_scores_codex":[0.9931372,0.002788009,0.001103959,0.001727491,0.0007680158,0.0004753035],"domain_scores_gemma":[0.9953163,0.0004029309,0.001618317,0.001644908,0.0008629956,0.0001545134],"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":[0.00005145555,0.0002462915,0.003414219,0.006498181,0.00009465669,0.00003338402,0.0008429593,0.9709815,0.0001682905,0.01734922,0.000002248419,0.0003175219],"study_design_scores_gemma":[0.001258441,0.0001234428,0.001788552,0.007044938,0.0004936726,0.000002122767,0.0008255473,0.9872989,0.0001279929,0.0005151537,0.000001135084,0.0005201249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.338039,0.0001011847,0.6601487,0.00003145461,0.0002246688,0.0007292411,0.000003124203,0.0000382169,0.0006844012],"genre_scores_gemma":[0.9976476,0.0001424128,0.0006664156,0.00002456072,0.00002701352,0.000009033974,0.0002561804,0.00002446605,0.001202322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6596086,"threshold_uncertainty_score":0.9996355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09601638270821015,"score_gpt":0.2466277321237235,"score_spread":0.1506113494155134,"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."}}