{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002416334,0.000248933,0.0002002572,0.0001824673,0.0002043465,0.0008433923,0.001226661,0.00006838985,0.0005560522],"category_scores_gemma":[0.000172314,0.000217645,0.00004957951,0.000174044,0.0000496662,0.0006043866,0.0002552929,0.0007772346,0.0004653224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008426362,"about_ca_system_score_gemma":0.00006377364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001749395,"about_ca_topic_score_gemma":0.000002814008,"domain_scores_codex":[0.9981458,0.0001160915,0.0003079272,0.0004737999,0.0005896954,0.0003667483],"domain_scores_gemma":[0.998859,0.0001817858,0.0002529506,0.0002945954,0.0002888265,0.0001227762],"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":[0.00007303282,0.00008313533,0.04985866,0.00002941942,0.0002183838,0.00006403576,0.001639984,0.7411642,0.00819745,0.1538632,0.001080065,0.04372847],"study_design_scores_gemma":[0.0007475715,0.000255073,0.002122056,0.0001845207,0.000004236049,0.00002107573,0.00008039359,0.9871492,0.0002908662,0.0004467488,0.008365401,0.0003328888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01789129,0.00002948547,0.9226633,0.003062324,0.000283008,0.0002065908,0.000001138975,0.0003529969,0.05550991],"genre_scores_gemma":[0.9517652,0.00001611328,0.04068546,0.0006534873,0.00007654795,0.000034414,0.00004938363,0.00002580862,0.006693529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.933874,"threshold_uncertainty_score":0.8875305,"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."}}