{"id":"W2185087676","doi":"10.13140/2.1.4274.3043","title":"Efficient Planning in MDPs by Small Backups","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"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; Artificial intelligence; Algorithm; Mathematics; Operating system","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001693425,0.00009720417,0.0000949617,0.000085435,0.00004198185,0.0001860779,0.0006357245,0.00004228853,0.0001405509],"category_scores_gemma":[0.00003370854,0.00008409137,0.00002255549,0.0002514624,0.00001816138,0.0001068746,0.0002381,0.0001417213,0.0008618009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004159041,"about_ca_system_score_gemma":0.00001873044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000118521,"about_ca_topic_score_gemma":0.000001224962,"domain_scores_codex":[0.9990386,0.00003036549,0.0002017989,0.0002330424,0.0001833471,0.0003128031],"domain_scores_gemma":[0.9994282,0.00008188059,0.00004700292,0.0003418688,0.00003042847,0.00007059799],"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":[3.31567e-7,0.00001563518,0.003173638,0.000003898509,0.000002293806,0.000003065689,0.0003769455,0.9844114,0.0006106107,0.003999426,0.006077649,0.001325139],"study_design_scores_gemma":[0.0001793536,0.00004394403,0.005279522,0.00001577648,4.621768e-7,0.000001518752,0.00004090099,0.992485,0.000281929,0.00005674694,0.001490715,0.0001241188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1017413,0.00002481644,0.8691801,0.0004224882,0.0001491544,0.0001477861,5.406833e-8,0.0001309285,0.02820338],"genre_scores_gemma":[0.9283842,0.000001127376,0.06611116,0.000595135,0.00001487188,0.00001460474,0.000001503147,0.000007477787,0.004869917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8266429,"threshold_uncertainty_score":0.9999161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01664528689941859,"score_gpt":0.2277813920581394,"score_spread":0.2111361051587208,"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."}}