{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00268216,0.0007608025,0.001187671,0.000487945,0.0006095612,0.0009185882,0.001421658,0.001129817,0.003250325],"category_scores_gemma":[0.01013439,0.0006363971,0.000694146,0.0005095432,0.001738968,0.001665158,0.001646151,0.002104615,0.0002690343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001498377,"about_ca_system_score_gemma":0.002129802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006555468,"about_ca_topic_score_gemma":0.005101517,"domain_scores_codex":[0.9991361,0.0003768374,0.00005378874,0.0001724554,0.0001729442,0.00008777484],"domain_scores_gemma":[0.9945126,0.004311447,0.0003532483,0.0002703901,0.0003819889,0.0001703262],"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":[0.00003455386,0.0000240223,0.0004210678,0.00005458824,0.00001793267,0.00003662278,0.00005336186,0.9521123,0.0003027953,0.03507217,0.0003687909,0.01150195],"study_design_scores_gemma":[0.000004557201,0.00000806092,0.00001699567,0.000002927747,0.00000142396,0.000002805533,0.000002509842,0.988847,0.0000735319,0.01092554,0.0001129139,0.000001711696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01087886,0.0001398982,0.9873555,0.0001924658,0.00002305621,0.00004181268,0.00004249674,0.0001817591,0.00114422],"genre_scores_gemma":[0.7727892,0.0003309979,0.2239672,0.0001799525,0.00004113248,0.0003007224,0.0002071152,0.0001038355,0.002079991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006555468,"threshold_uncertainty_score":0.01418483,"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."}}