{"id":"W4400488399","doi":"10.48550/arxiv.2407.06121","title":"Periodic agent-state based Q-learning for POMDPs","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Compute Canada","keywords":"State (computer science); Q-learning; Computer science; Mathematical optimization; Artificial intelligence; Mathematics; Algorithm; Reinforcement learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002978078,0.0003491981,0.000325007,0.0002623612,0.0003445175,0.0004759839,0.00172356,0.0001940627,0.00001060775],"category_scores_gemma":[0.00002102137,0.0003622375,0.0004359857,0.0005531529,0.00005150711,0.0001267931,0.003338194,0.001010537,0.00007977154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600773,"about_ca_system_score_gemma":0.0002605794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003522442,"about_ca_topic_score_gemma":0.00000963874,"domain_scores_codex":[0.9977164,0.000122065,0.000212908,0.001314194,0.0001005559,0.000533898],"domain_scores_gemma":[0.998556,0.0001776044,0.0001865497,0.0007659174,0.0001261443,0.0001877711],"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":[0.00001528587,0.00003480221,0.000281632,0.0003001521,0.00007377552,0.0004548025,0.0001551537,0.9829833,0.00001862186,0.012727,0.0007130177,0.00224247],"study_design_scores_gemma":[0.0002949188,0.00007407218,0.00009323159,0.0002147908,0.00004870517,0.00000307197,0.00001163237,0.9675593,0.00005034675,0.02414269,0.007098447,0.0004087774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2129169,0.0002608759,0.7827397,0.0003595757,0.001746235,0.0004503036,0.000006146852,0.0008768283,0.0006434837],"genre_scores_gemma":[0.9903388,0.00006273611,0.006215076,0.0001465535,0.0001955977,0.000002184959,0.00001292709,0.00003502956,0.0029911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.777422,"threshold_uncertainty_score":0.9998829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06035212277505819,"score_gpt":0.1934983825614182,"score_spread":0.13314625978636,"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."}}