{"id":"W4399728557","doi":"10.1109/tit.2024.3416063","title":"Reinforcement Learning for Near-Optimal Design of Zero-Delay Codes for Markov Sources","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Modular Robots and Swarm Intelligence","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Markov chain; Zero (linguistics); Computer science; Markov process; Markov decision process; Variable-order Markov model; Mathematical optimization; Algorithm; Markov model; Mathematics; Artificial intelligence; 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":[0.0004830564,0.0001275553,0.0001281444,0.0001550949,0.0001560198,0.00009398873,0.00009042895,0.00007378696,0.0001141456],"category_scores_gemma":[0.00001036529,0.0001187975,0.0001205759,0.0001042352,0.00003931223,0.0005115503,5.15749e-7,0.000130642,0.00003154337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000043707,"about_ca_system_score_gemma":0.00002798419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002106826,"about_ca_topic_score_gemma":2.530099e-7,"domain_scores_codex":[0.999254,0.00002029975,0.0003703866,0.00007117406,0.0001173556,0.0001667738],"domain_scores_gemma":[0.9993863,0.0003619577,0.00003790882,0.000107002,0.00007061473,0.00003620871],"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":[0.0001174594,0.000005504497,6.172047e-8,0.0003334391,0.00008425221,7.793974e-8,0.002261718,0.9227744,0.0003231445,0.003791841,0.0002669816,0.07004115],"study_design_scores_gemma":[0.0001568219,0.0001889055,2.852408e-7,0.0000774432,0.00003993801,0.000002781077,0.0002793362,0.9321547,0.05779635,0.0008602149,0.00831441,0.0001288381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008843148,0.00008235162,0.9971787,0.00001143598,0.0004782067,0.0005739803,0.00002871371,0.0002537727,0.0005084717],"genre_scores_gemma":[0.9833402,0.00006925504,0.01563618,0.00004222225,0.00001903229,0.0002850032,0.00001873625,0.00002325942,0.0005661141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9824559,"threshold_uncertainty_score":0.4844423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141723234347798,"score_gpt":0.2327273639614343,"score_spread":0.2185550405266545,"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."}}