{"id":"W3157613611","doi":"","title":"Online Sparse Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Reinforcement learning; Dimension (graph theory); Upper and lower bounds; Time horizon; Q-learning; Oracle; Mathematics; Lasso (programming language); Mathematical optimization; Computer science; Markov process; Combinatorics; Discrete mathematics; Artificial intelligence; Statistics","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007706407,0.0001498582,0.0002034316,0.0002096347,0.0001867663,0.0005560044,0.0004558353,0.00005856731,0.005444273],"category_scores_gemma":[0.008803629,0.0001297259,0.00004049105,0.0003066001,0.0002207622,0.0001965958,0.0002132516,0.0003600259,0.0006861209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005514658,"about_ca_system_score_gemma":0.0001852285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000229981,"about_ca_topic_score_gemma":0.000243561,"domain_scores_codex":[0.9967614,0.0001708451,0.0006843545,0.0005054419,0.001616356,0.0002616357],"domain_scores_gemma":[0.9961553,0.001476111,0.0001674036,0.0002569645,0.001794923,0.0001493483],"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":[0.00008131028,0.0001257275,0.0001338465,0.000001849495,0.00001914623,0.0001441214,0.0002482729,0.02006389,0.0005229427,0.5086488,0.0004327381,0.4695774],"study_design_scores_gemma":[0.00003982033,0.0001505419,0.000285902,0.00002433172,0.000003644799,0.00002011583,0.003225774,0.545452,0.003981931,0.4394213,0.007235308,0.0001593471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002495149,0.00002423779,0.9870315,0.001999762,0.0006009514,0.00008122922,0.000150016,0.00002368778,0.007593464],"genre_scores_gemma":[0.9681119,0.000445561,0.0203363,0.0003186816,0.00020867,0.000007851381,0.000153691,0.00001153603,0.01040579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9666952,"threshold_uncertainty_score":0.9995456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4004819125429087,"score_gpt":0.497299212462624,"score_spread":0.09681729991971538,"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."}}