{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001646073,0.0005268604,0.000652834,0.0003411701,0.0003214681,0.0006556635,0.0006712708,0.0007851409,0.001398892],"category_scores_gemma":[0.006345716,0.0003155987,0.0002870398,0.0002477003,0.001880226,0.0007834597,0.0009995569,0.001041054,0.0001630528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001342701,"about_ca_system_score_gemma":0.001559865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002850323,"about_ca_topic_score_gemma":0.001984369,"domain_scores_codex":[0.9995154,0.0001721077,0.00002301383,0.0000934393,0.0001251025,0.00007095943],"domain_scores_gemma":[0.9970994,0.002156548,0.0002703385,0.00008265304,0.0002888721,0.0001022385],"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":[0.00006642133,0.00003196515,0.0002951219,0.00006034405,0.00001065107,0.00003737725,0.00007733735,0.9418461,0.002120908,0.04221236,0.0002482309,0.01299316],"study_design_scores_gemma":[0.000009519876,0.00002291355,0.00002045058,0.000005498726,0.000001469013,0.000004627963,0.000003965769,0.9923867,0.00031952,0.007123951,0.00009827415,0.000003093556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02029799,0.0001133815,0.9780903,0.0001676816,0.00001709276,0.00003230786,0.00001247898,0.00007950071,0.001189352],"genre_scores_gemma":[0.9312413,0.0001434888,0.06694358,0.00009444647,0.00001311439,0.0001018776,0.0000252724,0.00002510808,0.001411836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002850323,"threshold_uncertainty_score":0.009742022,"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."}}