{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002485635,0.001172952,0.001240019,0.0006849431,0.0004760285,0.001177212,0.001723951,0.001129972,0.002439478],"category_scores_gemma":[0.01228546,0.0007530269,0.0009454353,0.0005573228,0.00198413,0.003330389,0.002891295,0.002181762,0.0003973169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004116,"about_ca_system_score_gemma":0.001456949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003602405,"about_ca_topic_score_gemma":0.00414749,"domain_scores_codex":[0.9987227,0.0005238284,0.00006400351,0.0003633653,0.0002359171,0.00009004131],"domain_scores_gemma":[0.9924873,0.004501818,0.0007703457,0.001499991,0.0005295504,0.0002109391],"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":[0.0004813549,0.0001956785,0.002811812,0.000137098,0.000107963,0.0001805687,0.0003087043,0.8326565,0.006396874,0.03137887,0.001462856,0.1238817],"study_design_scores_gemma":[0.00001323599,0.0000283763,0.00009163161,0.000007413929,0.000005423722,0.00001645728,0.00000830823,0.9868362,0.0009521545,0.01167815,0.0003555325,0.000007178771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02910625,0.0001714764,0.967958,0.0002546897,0.00004684311,0.00006920176,0.000101976,0.001240586,0.001050986],"genre_scores_gemma":[0.7635284,0.0001081078,0.2343967,0.0001703637,0.00004610542,0.0001973157,0.0003253335,0.0001367964,0.00109091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003602405,"threshold_uncertainty_score":0.01314545,"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."}}