{"id":"W7123357605","doi":"10.1109/cdc57313.2025.11312431","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Convergence (economics); Salient; Regularization (linguistics); Reinforcement learning; State (computer science); Fixed point; Stationary point","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001568202,0.0004067537,0.0007602251,0.0007006363,0.0001336567,0.0001472249,0.001751706,0.0001870077,0.0001163146],"category_scores_gemma":[0.0004954127,0.0004365247,0.0002560119,0.002487174,0.0003125315,0.0003559981,0.000632592,0.0006156492,0.00004901512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002989257,"about_ca_system_score_gemma":0.001421777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005006893,"about_ca_topic_score_gemma":0.0001140331,"domain_scores_codex":[0.9957401,0.0006528514,0.001200059,0.001017375,0.0005394838,0.0008501221],"domain_scores_gemma":[0.9974802,0.0005045727,0.0004589538,0.001020823,0.0003969698,0.0001385343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008643089,0.002334177,0.1152373,0.0008928802,0.0005785807,0.0003076513,0.003368295,0.03765019,0.0183316,0.2590096,0.0003591221,0.5610663],"study_design_scores_gemma":[0.003529783,0.0002420966,0.01285637,0.0003362175,0.00003368074,9.157188e-7,0.00005757426,0.975263,0.003119358,0.002058229,0.002148353,0.0003544103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03031672,0.0004715527,0.9631988,0.001985359,0.0008897537,0.0008238795,0.000002330359,0.0002368173,0.002074831],"genre_scores_gemma":[0.9117562,0.00003007331,0.0807742,0.000550409,0.0000088188,0.00003557924,0.000002400238,0.00001507997,0.00682728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9376128,"threshold_uncertainty_score":0.9998087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007703628012805853,"score_gpt":0.2450067562005608,"score_spread":0.2373031281877549,"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."}}