{"id":"W3181012797","doi":"10.1609/aaai.v36i6.20660","title":"Learning Expected Emphatic Traces for Deep RL","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Weighting; Scalability; Convergence (economics); Stability (learning theory); Artificial intelligence; Machine learning; Sampling (signal processing); Sample (material); Artificial neural network; Baseline (sea); Key (lock); Variance (accounting); Algorithm; Computer vision","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":[0.0007094426,0.0002136392,0.0002565693,0.0001662897,0.0007980448,0.0002843734,0.002688108,0.00004743001,0.0001472379],"category_scores_gemma":[0.0006209271,0.0001827303,0.0001541231,0.0007835826,0.0001470173,0.0003574524,0.0007129615,0.0004534179,0.000025233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009219248,"about_ca_system_score_gemma":0.00009647871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001127288,"about_ca_topic_score_gemma":0.000001759725,"domain_scores_codex":[0.9977809,0.00003951432,0.0005690593,0.000481527,0.0007126877,0.0004162985],"domain_scores_gemma":[0.9983725,0.0002468976,0.0005734891,0.0002717932,0.0004656659,0.00006968242],"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":[0.00007280125,0.0001054383,0.0002206965,0.0000537223,0.00002725837,4.128016e-7,0.007708056,0.1664832,0.01496478,0.7729211,0.0001180452,0.0373244],"study_design_scores_gemma":[0.00004781368,0.0007728122,0.00005795711,0.00004996344,0.00001496908,0.000005343334,0.003944975,0.8554875,0.1109324,0.02784414,0.0005891024,0.0002530302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09160624,0.00004368549,0.8926318,0.003568623,0.001084123,0.001222663,0.000002703561,0.0003269036,0.009513237],"genre_scores_gemma":[0.9920481,0.000009932454,0.006508832,0.0001552731,0.00004874566,0.0001732813,0.000001110036,0.00001822321,0.001036466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9004419,"threshold_uncertainty_score":0.7451524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0655002341992619,"score_gpt":0.2902482295044936,"score_spread":0.2247479953052317,"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."}}