{"id":"W3039671729","doi":"10.48550/arxiv.2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Reinforcement learning; Computer science; Coda; Representation (politics); Artificial intelligence; Set (abstract data type); Causal structure; Sequence (biology); Machine learning; State space; Mathematics","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":[0.0001867981,0.0003458631,0.0003167388,0.0001650672,0.0001586951,0.0003588797,0.00462954,0.0002524238,0.00002804086],"category_scores_gemma":[0.00006634178,0.0004350323,0.00009101578,0.0004205541,0.00009993385,0.0009852996,0.007518952,0.0007052384,0.0000908151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00069918,"about_ca_system_score_gemma":0.0004348622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002047384,"about_ca_topic_score_gemma":0.00003186798,"domain_scores_codex":[0.9976895,0.0001216664,0.0002857112,0.001348133,0.000213579,0.0003414307],"domain_scores_gemma":[0.996928,0.0000919355,0.0004352681,0.002228609,0.0001407088,0.0001754695],"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":[0.00001706642,0.00001638732,0.001051401,0.00005884258,0.00009930167,0.0001164819,0.0002021153,0.985586,0.0000307346,0.01247909,0.0001437757,0.0001987765],"study_design_scores_gemma":[0.0003637101,0.00004576068,0.0002545413,0.00006878744,0.00008350177,0.000003001189,0.0001102467,0.9974291,0.00002732388,0.00104689,0.0001513181,0.0004157597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03362774,0.000009059688,0.9641995,0.0001038035,0.0008441343,0.000291215,0.0000665858,0.0003022701,0.0005556449],"genre_scores_gemma":[0.9865797,0.00004108387,0.01231197,0.0001406482,0.00006798185,1.434358e-7,0.0005117678,0.00002626207,0.0003204565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.952952,"threshold_uncertainty_score":0.9998102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2323526430308347,"score_gpt":0.2381296332051483,"score_spread":0.005776990174313573,"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."}}