{"id":"W2593237273","doi":"10.1609/aaai.v32i1.11631","title":"Multi-Step Reinforcement Learning: A Unifying Algorithm","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; DeepMind","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":true,"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":[0.0007418666,0.000309026,0.0002912106,0.0001948037,0.000495519,0.0004152124,0.002859985,0.0001209567,0.0001257517],"category_scores_gemma":[0.000633862,0.000242286,0.000141166,0.0008994911,0.0005071139,0.0005502939,0.0009153195,0.0005507913,0.0004037424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009122324,"about_ca_system_score_gemma":0.0001222704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005174801,"about_ca_topic_score_gemma":0.000003825049,"domain_scores_codex":[0.9972612,0.00002945142,0.0007430391,0.0005864651,0.0008140761,0.0005658161],"domain_scores_gemma":[0.9975198,0.00008706097,0.0006487655,0.0004544693,0.001158748,0.0001311774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005289292,0.0001479687,0.0003982802,0.0000670603,0.00006339402,0.000001475817,0.004897086,0.02834892,0.02942686,0.7260391,0.0002988776,0.2102581],"study_design_scores_gemma":[0.00004546647,0.0004822668,0.00007046048,0.0001787651,0.00001013259,0.000004298136,0.0004791254,0.8288441,0.1661968,0.002635838,0.0008069917,0.0002457839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002891157,0.000007234223,0.9794903,0.001036294,0.0006558921,0.0004158699,4.018624e-7,0.0002000973,0.01530271],"genre_scores_gemma":[0.9133315,0.00002413619,0.08332956,0.0002385959,0.0001348117,0.00001988864,5.478779e-7,0.00001963346,0.002901307],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9104404,"threshold_uncertainty_score":0.9880135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09247718432083181,"score_gpt":0.3136361361909427,"score_spread":0.2211589518701109,"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."}}