{"id":"W1870822514","doi":"","title":"A Deeper Look at Planning as Learning from Replay","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Markov decision process; Function (biology); Temporal difference learning; Markov chain; Equivalence (formal languages); Artificial intelligence; Markov process; Machine learning; Mathematical optimization; 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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006121803,0.0003173217,0.0002641012,0.0002656038,0.0002931421,0.0005763469,0.001480363,0.0001262962,0.0008789888],"category_scores_gemma":[0.001417422,0.0003121443,0.00009739104,0.0001914145,0.00006039967,0.000606096,0.0008785866,0.001234068,0.002225579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003370574,"about_ca_system_score_gemma":0.0001619256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003531452,"about_ca_topic_score_gemma":0.00001004438,"domain_scores_codex":[0.9969473,0.0002907915,0.000436358,0.0007236364,0.001187111,0.0004148158],"domain_scores_gemma":[0.9982561,0.0003149444,0.0003828006,0.0004333511,0.0003502779,0.000262551],"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":[0.00008889432,0.00002196051,0.05406003,0.000002373339,0.0000759395,0.0001178712,0.00251459,0.8924187,0.000575754,0.04710869,0.0003243824,0.002690773],"study_design_scores_gemma":[0.0008487828,0.0003712697,0.001310515,0.0001199446,0.000008131918,0.0000408134,0.0002549645,0.9564802,0.00037146,0.002431234,0.03738575,0.0003769441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08525012,0.0001053673,0.71848,0.002377513,0.00133237,0.0001574967,0.000002010042,0.0007091971,0.1915859],"genre_scores_gemma":[0.9658251,0.00001834301,0.009287778,0.0006778809,0.0002293661,0.0000144695,0.0001283359,0.0000344765,0.02378424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.880575,"threshold_uncertainty_score":0.9999331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07534542055669481,"score_gpt":0.3228219604417945,"score_spread":0.2474765398850997,"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."}}