{"id":"W2990933479","doi":"10.48550/arxiv.1911.08610","title":"Efficient decorrelation of features using Gramian in Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Decorrelation; Regularization (linguistics); Computer science; Sample complexity; Artificial intelligence; Gramian matrix; Temporal difference learning; Computational complexity theory; Mathematical optimization; Machine learning; Mathematics; Algorithm","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":[0.002213595,0.001025943,0.001472419,0.0004468763,0.0004861296,0.0006939817,0.001129305,0.001142382,0.001234688],"category_scores_gemma":[0.0099709,0.0005368267,0.0005357412,0.0004365878,0.002212024,0.001601441,0.001709083,0.001963512,0.0002978451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009250746,"about_ca_system_score_gemma":0.001200707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002559814,"about_ca_topic_score_gemma":0.002677821,"domain_scores_codex":[0.9986285,0.000708038,0.00005304707,0.0002510733,0.0002254534,0.0001338348],"domain_scores_gemma":[0.9964319,0.002410076,0.0003540989,0.0003872926,0.0002497117,0.0001668369],"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":[0.0002523603,0.0001463454,0.001252667,0.00006928058,0.00004802556,0.0001328352,0.0001049447,0.9010121,0.005026169,0.02598403,0.001081824,0.06488939],"study_design_scores_gemma":[0.00001427497,0.00004632634,0.00007601668,0.000004027595,0.000003767111,0.0000119021,0.000004200072,0.9891968,0.0006336817,0.009872011,0.0001302631,0.00000652995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05032786,0.0001468265,0.9475375,0.0002666705,0.00002741705,0.00005707064,0.00003248542,0.0004668107,0.00113735],"genre_scores_gemma":[0.8746221,0.00009380962,0.1232553,0.0001613125,0.00002876286,0.0001438116,0.00006741965,0.00007790734,0.001549714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002559814,"threshold_uncertainty_score":0.01170677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05318134821492707,"score_gpt":0.2026254375092948,"score_spread":0.1494440892943678,"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."}}