{"id":"W4401693038","doi":"10.1109/isit57864.2024.10619668","title":"Reinforcement Learning for Near-Optimal Design of Zero-Delay Codes for Markov Sources","year":2024,"lang":"en","type":"article","venue":"","topic":"Modular Robots and Swarm Intelligence","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Zero (linguistics); Computer science; Markov chain; Markov process; Markov decision process; Variable-order Markov model; Markov model; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning; Statistics","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":[0.0002554775,0.0001135939,0.000145135,0.00004476995,0.00005964634,0.00007155449,0.00009376498,0.0000514055,0.0001439242],"category_scores_gemma":[0.00002889383,0.00009552091,0.0000902784,0.00006037811,0.0000229151,0.00007077288,0.00001454308,0.00006814082,0.000009257798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000199722,"about_ca_system_score_gemma":0.00001657673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001008198,"about_ca_topic_score_gemma":8.729629e-7,"domain_scores_codex":[0.9993399,0.000007245933,0.0002248681,0.0001322289,0.00008746001,0.000208347],"domain_scores_gemma":[0.9996113,0.0002069057,0.0000147135,0.00009163565,0.00003921377,0.00003629671],"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":[0.00002137123,0.000003080763,0.000005818738,0.000321935,0.00007152618,6.858371e-7,0.0004019234,0.9786175,0.002985748,0.00316701,0.003202375,0.01120101],"study_design_scores_gemma":[0.00007453754,0.0001648195,0.000001440036,0.00005033434,0.00002182374,0.000001768754,0.00006394129,0.9380662,0.03629526,0.0002126913,0.02492915,0.0001180483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003180365,0.0006398811,0.9942287,0.00001909434,0.0001711686,0.0004374037,0.000002827123,0.0002180054,0.001102539],"genre_scores_gemma":[0.8762963,0.00006245442,0.1186862,0.00001881198,0.00004868034,0.0001095954,0.00001116337,0.00003954893,0.00472723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8755425,"threshold_uncertainty_score":0.389523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02413141262267032,"score_gpt":0.2514654987269101,"score_spread":0.2273340861042398,"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."}}