{"id":"W2963828709","doi":"10.48550/arxiv.1703.01327","title":"Multi-step Reinforcement Learning: A Unifying Algorithm","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Backup; Algorithm; TRACE (psycholinguistics); Sampling (signal processing); Focus (optics); Monte Carlo method; Importance sampling; Artificial intelligence; Machine learning; 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":[0.004531997,0.001188306,0.001674645,0.0008396695,0.0006097578,0.001355883,0.003307166,0.002346471,0.002417129],"category_scores_gemma":[0.01007172,0.0006054158,0.0008304904,0.0006262771,0.001770446,0.00277364,0.00305521,0.003128151,0.0006646661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348125,"about_ca_system_score_gemma":0.002275206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002289575,"about_ca_topic_score_gemma":0.002148053,"domain_scores_codex":[0.9979808,0.0005960808,0.0001335397,0.0005744987,0.0005347328,0.0001804832],"domain_scores_gemma":[0.9966968,0.002049168,0.0002093267,0.0005162494,0.0003428855,0.0001854795],"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":[0.0002124146,0.0001860028,0.00132233,0.0001147706,0.00006961561,0.00007407265,0.0002071703,0.6845416,0.002550806,0.09311544,0.001816174,0.2157896],"study_design_scores_gemma":[0.00002067954,0.00004166348,0.00002935244,0.000009154924,0.000005421021,0.00001368784,0.000004214984,0.9863766,0.0004949665,0.0125006,0.0004977522,0.00000590782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004828889,0.0001189792,0.9931251,0.0001862978,0.00002674612,0.00005850564,0.00001061212,0.0004922294,0.001152681],"genre_scores_gemma":[0.3091453,0.0001951748,0.6867846,0.0003533253,0.00007673487,0.000333748,0.00007956664,0.0002220892,0.002809444],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004531997,"threshold_uncertainty_score":0.02396774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09250465055229885,"score_gpt":0.2190304302502291,"score_spread":0.1265257796979303,"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."}}