{"id":"W1602154927","doi":"10.48550/arxiv.1301.2343","title":"Planning by Prioritized Sweeping with Small Backups","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Business; Computer science; Process management","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":[0.0002272998,0.0004463652,0.0004371346,0.0002353307,0.0002246342,0.0004239508,0.002513026,0.00031591,0.00003019768],"category_scores_gemma":[0.00003455062,0.0004825341,0.0001345677,0.0004694804,0.000121945,0.0004874619,0.002259073,0.001017195,0.0001886493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002412694,"about_ca_system_score_gemma":0.0002111067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001490524,"about_ca_topic_score_gemma":0.000003323243,"domain_scores_codex":[0.997636,0.0001362169,0.0002598171,0.00121022,0.0001620073,0.000595751],"domain_scores_gemma":[0.9975467,0.0001577251,0.0004352602,0.001430837,0.0001950233,0.0002344531],"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":[0.00001494068,0.00001883309,0.002946601,0.00007813598,0.0001020306,0.0001819581,0.0002733672,0.9816989,0.00003645994,0.01371402,0.0007493129,0.0001854264],"study_design_scores_gemma":[0.0008380897,0.00009974433,0.0004898331,0.0003965916,0.0000618112,0.000008153706,0.00007745908,0.9932662,0.00009351088,0.001364545,0.002532314,0.0007717116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08602908,0.0000622758,0.9075045,0.00007531168,0.0003895656,0.0004073798,0.000002428197,0.0004689955,0.005060476],"genre_scores_gemma":[0.9598354,0.00006486817,0.03211585,0.0001681953,0.00009399778,0.000002150217,0.00003308604,0.00004278696,0.007643652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8753886,"threshold_uncertainty_score":0.9997627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07880461453518656,"score_gpt":0.1824405861278815,"score_spread":0.1036359715926949,"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."}}