{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003248615,0.0002291367,0.0002042792,0.0001581865,0.001260489,0.0004570763,0.002559197,0.0001077086,0.00004355414],"category_scores_gemma":[0.0001465664,0.0002611924,0.0001265866,0.0002277092,0.0001531987,0.001360738,0.001234464,0.0003919996,0.0003672173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001587513,"about_ca_system_score_gemma":0.00007868621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000160733,"about_ca_topic_score_gemma":0.000008760825,"domain_scores_codex":[0.9984516,0.0000778037,0.0001950579,0.0006294104,0.0001496147,0.0004964932],"domain_scores_gemma":[0.9976344,0.00006359884,0.0003923214,0.001575753,0.0001358046,0.0001981979],"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":[0.000004928625,0.00001933502,0.004457998,0.000009683474,0.0000395155,0.0001931043,0.0001683195,0.9633358,0.00004955169,0.0280819,0.00007577294,0.003564068],"study_design_scores_gemma":[0.000976553,0.0001080193,0.002536079,0.00003013332,0.00001873323,0.000005852884,0.00009164579,0.9900383,0.0001036598,0.00009973636,0.005676522,0.0003148002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003604542,0.000007937349,0.9871191,0.00008929949,0.0003706131,0.0001693323,2.456936e-7,0.0002930562,0.008345827],"genre_scores_gemma":[0.9297976,0.00005156868,0.04169729,0.00007199572,0.00004452097,5.04876e-7,0.00000306983,0.00001582871,0.02831756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9454219,"threshold_uncertainty_score":0.999984,"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."}}