{"id":"W4210257517","doi":"10.1109/cdc45484.2021.9682777","title":"Convergence and Near Optimality of Q-Learning with Finite Memory for Partially Observed Models","year":2021,"lang":"en","type":"article","venue":"2021 60th IEEE Conference on Decision and Control (CDC)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Markov decision process; Convergence (economics); Computer science; Quantization (signal processing); Q-learning; Mathematical optimization; Limit (mathematics); State space; Optimal control; Markov process; Mathematics; Algorithm; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0006117236,0.0002480223,0.0005066342,0.00006174688,0.00023518,0.0003959007,0.0004087675,0.0001123664,0.00007803965],"category_scores_gemma":[0.0004490551,0.0002105851,0.00007802839,0.0002333246,0.0001615298,0.000423442,0.0001421698,0.0002533551,0.000007547641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000164705,"about_ca_system_score_gemma":0.0003725675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000132847,"about_ca_topic_score_gemma":0.00001541246,"domain_scores_codex":[0.9978358,0.0001789138,0.0004888673,0.0006610516,0.0004911586,0.0003441882],"domain_scores_gemma":[0.997158,0.001102621,0.0002776366,0.0005697267,0.0006935975,0.0001984443],"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":[0.000426236,0.00005089507,0.001019661,0.00005090361,0.00007191636,0.0000321195,0.0004392235,0.9371853,0.001461527,0.02290118,0.00006221409,0.03629878],"study_design_scores_gemma":[0.002823459,0.0006074453,0.001059241,0.0001802995,0.00003362876,0.000007743752,0.000122592,0.9917185,0.001182854,0.001613018,0.0003993941,0.0002517795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05418345,0.0001710524,0.9440057,0.0004459162,0.0001798626,0.0003131023,0.000005869905,0.0000373172,0.0006577703],"genre_scores_gemma":[0.9599501,0.000262752,0.03870192,0.0003161638,0.00002474761,0.00003069022,0.000004475181,0.00001393095,0.0006951657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9057667,"threshold_uncertainty_score":0.8587413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06092869236888402,"score_gpt":0.2648753527444318,"score_spread":0.2039466603755478,"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."}}