{"id":"W2963462732","doi":"","title":"Planning by Prioritized Sweeping with Small Backups","year":2013,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Backup; Successor cardinal; Computer science; Reinforcement learning; Flexibility (engineering); Computation; Implementation; Process (computing); Distributed computing; State (computer science); Artificial intelligence; Algorithm; 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":[0.0009385318,0.0007804367,0.0008157133,0.0004247113,0.000481579,0.0007641969,0.001458344,0.0006591963,0.005164178],"category_scores_gemma":[0.003668572,0.0004869588,0.0004498323,0.0003838242,0.0009507725,0.001430004,0.001505349,0.001540369,0.0005651854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004671958,"about_ca_system_score_gemma":0.001293916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002719353,"about_ca_topic_score_gemma":0.003098011,"domain_scores_codex":[0.9994961,0.0001143017,0.00004062231,0.0001273002,0.0001387329,0.00008301013],"domain_scores_gemma":[0.9982339,0.0008953833,0.0001427202,0.0004440965,0.0001341972,0.0001496989],"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":[0.0009631538,0.000233665,0.001472353,0.0001891261,0.00006277036,0.0002940925,0.0002748831,0.7062021,0.02083912,0.02635902,0.002514978,0.2405948],"study_design_scores_gemma":[0.00006826109,0.00008937803,0.0001290037,0.00001124561,0.00001343824,0.00004721026,0.00002538364,0.9798544,0.003728308,0.01481196,0.001209849,0.00001154878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06015171,0.0002297266,0.9341944,0.0002138951,0.00008121847,0.00009770814,0.0001049468,0.002310761,0.0026157],"genre_scores_gemma":[0.7448787,0.0001241302,0.2525284,0.00009963955,0.00002702285,0.000176511,0.0001359571,0.0001935698,0.001836012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005164178,"threshold_uncertainty_score":0.01727587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03698794599683398,"score_gpt":0.2714415493679603,"score_spread":0.2344536033711264,"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."}}