{"id":"W2744625767","doi":"10.48550/arxiv.1708.01298","title":"Effective sketching methods for value function approximation","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Sketch; Computer science; Reinforcement learning; Variety (cybernetics); Function (biology); Matrix (chemical analysis); Coding (social sciences); Artificial intelligence; Machine learning; Algorithm; Theoretical computer science; 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":[0.001240464,0.0003082139,0.0003441294,0.0002581415,0.0005249811,0.0003956124,0.001802674,0.0003324532,0.000003922454],"category_scores_gemma":[0.0003718021,0.0003603983,0.0002787786,0.0001681129,0.00006926464,0.00076278,0.001607959,0.0005838328,0.00002844504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003371419,"about_ca_system_score_gemma":0.000125368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004818548,"about_ca_topic_score_gemma":0.000001406209,"domain_scores_codex":[0.9979824,0.0003908145,0.0001986404,0.001011673,0.00008694924,0.0003295638],"domain_scores_gemma":[0.9969144,0.0005212622,0.0006645998,0.001573469,0.0002275794,0.00009862528],"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":[0.00002556738,0.00001382839,0.0001157714,0.000127525,0.00009729947,0.000003841227,0.0001682928,0.8040752,0.00004957982,0.1819659,0.00004240904,0.01331473],"study_design_scores_gemma":[0.0004278675,0.0001119679,0.0005628124,0.00009702629,0.0001200683,0.000001110425,0.00001588093,0.9132786,0.0002458008,0.08377925,0.001024353,0.0003353076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002074589,0.00002729514,0.9912142,0.00005079958,0.001981546,0.001206491,0.000002004711,0.0003163387,0.003126727],"genre_scores_gemma":[0.7467034,0.00002643403,0.2510667,0.00005220004,0.0001592383,0.00001181195,0.00003053623,0.00002696009,0.001922692],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7446288,"threshold_uncertainty_score":0.9998848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08423265039614783,"score_gpt":0.263671457935536,"score_spread":0.1794388075393882,"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."}}