{"id":"W3168260200","doi":"10.48550/arxiv.2106.11779","title":"Emphatic Algorithms for Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Temporal difference learning; Artificial intelligence; Weighting; Convergence (economics); Context (archaeology); Algorithm; Machine learning; Stability (learning theory); Lambda; Function (biology)","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":[0.0002142309,0.0001674658,0.0001797246,0.0001087077,0.0003066921,0.000136111,0.0007002781,0.00007483185,0.00006609229],"category_scores_gemma":[0.0001531239,0.0002013277,0.0001407884,0.000668989,0.00004399629,0.0005581033,0.0003832281,0.0001701231,0.0001167598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447016,"about_ca_system_score_gemma":0.000120026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007382428,"about_ca_topic_score_gemma":0.000003414303,"domain_scores_codex":[0.9986619,0.00007507734,0.0001885437,0.0005495238,0.0001124748,0.0004124233],"domain_scores_gemma":[0.9987159,0.0001936383,0.0001412256,0.0005824125,0.0002318625,0.0001349036],"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":[0.000005329089,0.00001383403,0.0005476751,0.00002035439,0.00003899623,0.00009481871,0.0001797944,0.8828484,0.00005902376,0.1151683,0.00007799817,0.0009454397],"study_design_scores_gemma":[0.0007237847,0.000127797,0.0001345715,0.00001948433,0.00002780173,0.000008551938,0.0001686226,0.9913324,0.0006555593,0.001268052,0.005290443,0.0002429288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002975138,0.00003090353,0.9920002,0.0001019513,0.000309307,0.0001758845,1.653574e-7,0.0002089692,0.004197453],"genre_scores_gemma":[0.9627028,0.00005198802,0.01809566,0.0001988495,0.00004924288,0.000001385771,0.00001389277,0.00001477889,0.01887144],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9739046,"threshold_uncertainty_score":0.8209905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06650257069781514,"score_gpt":0.2029712036247547,"score_spread":0.1364686329269396,"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."}}