{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009177895,0.0007743019,0.0008364636,0.000407804,0.0004598393,0.0007815887,0.001461896,0.0006992776,0.004728744],"category_scores_gemma":[0.003672868,0.0004850331,0.0004498576,0.0003838275,0.001027409,0.001458067,0.001616481,0.0015655,0.0005646871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004740572,"about_ca_system_score_gemma":0.001190933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002516359,"about_ca_topic_score_gemma":0.002841695,"domain_scores_codex":[0.9994864,0.0001196616,0.00003968818,0.0001357807,0.0001387049,0.00007969283],"domain_scores_gemma":[0.9983522,0.0008128834,0.0001392431,0.0004291642,0.0001213701,0.000145148],"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":[0.0008348111,0.0002288727,0.001461911,0.0001774046,0.00006291969,0.0002703402,0.000249243,0.7350071,0.01973006,0.02919704,0.002322451,0.2104579],"study_design_scores_gemma":[0.0000612866,0.00007983413,0.0001210294,0.000009894447,0.00001183326,0.00004232739,0.00002230293,0.9789473,0.003133829,0.01653874,0.001021808,0.000009983117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0633699,0.0002209747,0.9311225,0.0002249024,0.00007593296,0.0000879498,0.0000954901,0.002046984,0.002755309],"genre_scores_gemma":[0.764391,0.000123039,0.2330527,0.00009567505,0.00002759178,0.0001586617,0.0001217811,0.000164031,0.001865425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004728744,"threshold_uncertainty_score":0.01581919,"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."}}