{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003187149,0.001308748,0.001376767,0.001088478,0.0004765172,0.001791026,0.001521355,0.001788523,0.006271408],"category_scores_gemma":[0.02211949,0.0008161705,0.0008422927,0.001072444,0.001784355,0.003137549,0.002696977,0.003207682,0.001428513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125119,"about_ca_system_score_gemma":0.00110851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001892874,"about_ca_topic_score_gemma":0.001939151,"domain_scores_codex":[0.9985064,0.0006637602,0.00009947707,0.0002179873,0.000434276,0.00007814691],"domain_scores_gemma":[0.9914034,0.006282633,0.0004171273,0.001127007,0.0005629616,0.0002070376],"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":[0.0001034106,0.00005862922,0.000723782,0.0002910732,0.00005805995,0.00006601353,0.0001856652,0.6436613,0.002473397,0.1826173,0.002908292,0.166853],"study_design_scores_gemma":[0.00001844293,0.00002365237,0.00004411745,0.00002897745,0.00000556944,0.00002038748,0.00001180017,0.9363264,0.0005581991,0.06135891,0.001594508,0.000009060081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001950672,0.0003417351,0.9963619,0.0001152026,0.00002374438,0.00002381448,0.0000285006,0.0002444547,0.000909937],"genre_scores_gemma":[0.2434074,0.001275891,0.7503482,0.0001779662,0.000109182,0.0003619343,0.0002650541,0.0003363247,0.003718089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006271408,"threshold_uncertainty_score":0.02098,"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."}}