{"id":"W3190031629","doi":"10.48550/arxiv.2108.02827","title":"An Elementary Proof that Q-learning Converges Almost Surely","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Q-learning; Function (biology); Bellman equation; Field (mathematics); Computer science; State (computer science); Value (mathematics); Elementary proof; Mathematical economics; Artificial intelligence; Connection (principal bundle); Mathematics; Discrete mathematics; Algorithm; Machine learning; Pure mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006712706,0.002081271,0.001908525,0.001727962,0.001387221,0.002295859,0.002232123,0.002526441,0.02201591],"category_scores_gemma":[0.05504093,0.0009381562,0.002912133,0.001621399,0.005178094,0.007094299,0.004969806,0.008624305,0.004145647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002182004,"about_ca_system_score_gemma":0.0030689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003251025,"about_ca_topic_score_gemma":0.002916284,"domain_scores_codex":[0.9965336,0.001008596,0.0001941755,0.0007166824,0.001160888,0.000385989],"domain_scores_gemma":[0.967644,0.02590011,0.001027607,0.001510301,0.003350599,0.0005673761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006412835,0.0001034581,0.0008019974,0.0003788393,0.00009005429,0.0002090373,0.0003159887,0.02685959,0.000891291,0.9273881,0.01399392,0.02890363],"study_design_scores_gemma":[0.00006118927,0.00005566253,0.0002840581,0.0001286412,0.00002254676,0.0001767517,0.00003809142,0.07122573,0.0005255175,0.9192944,0.008155571,0.00003188277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00593015,0.00117714,0.9544432,0.007041969,0.0005274266,0.000130704,0.0004574115,0.0003481977,0.02994381],"genre_scores_gemma":[0.5146421,0.006420852,0.4208215,0.01276944,0.002389431,0.00204862,0.001016523,0.0009407551,0.03895086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02201591,"threshold_uncertainty_score":0.07365054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07020033359668047,"score_gpt":0.1984780508432303,"score_spread":0.1282777172465498,"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."}}