{"id":"W2568999269","doi":"10.1609/aaai.v30i1.10311","title":"Incremental Stochastic Factorization for Online Reinforcement Learning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Reinforcement learning; Computer science; Non-negative matrix factorization; Probabilistic logic; Multiplicative function; Factorization; Divergence (linguistics); Bellman equation; Markov chain; Artificial intelligence; Markov process; Algorithm; Mathematical optimization; Theoretical computer science; Machine learning; Matrix decomposition; Mathematics; Eigenvalues and eigenvectors","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":[0.0003944895,0.000215452,0.0002145298,0.0001281427,0.0002380969,0.00015928,0.001477672,0.0000756403,0.00005373303],"category_scores_gemma":[0.001091892,0.0001363711,0.0001094446,0.0003454491,0.0001507048,0.0005138253,0.0003788298,0.0001756605,0.00004159259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001173292,"about_ca_system_score_gemma":0.00008207084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008888307,"about_ca_topic_score_gemma":0.000001725997,"domain_scores_codex":[0.9980616,0.00001359827,0.0005930647,0.0004014802,0.0005621952,0.0003680709],"domain_scores_gemma":[0.9982865,0.0001958392,0.0005468812,0.0002360718,0.0006578111,0.00007686178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006992203,0.00006269114,0.0001444362,0.0000355985,0.00002365513,6.847533e-8,0.0005541049,0.0644859,0.1035895,0.7715538,0.00006285529,0.05941754],"study_design_scores_gemma":[0.0001131015,0.0007565454,0.000126881,0.0004133569,0.00001742981,0.000001618189,0.0002421764,0.651472,0.3200321,0.02629586,0.0002243142,0.0003046846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.012608,0.000002843633,0.9835864,0.00178361,0.0004186894,0.0005761203,0.000002610929,0.0001047702,0.0009169755],"genre_scores_gemma":[0.9932355,0.00001242052,0.005619089,0.00009665315,0.0000830889,0.00003433677,0.000001679439,0.00001497579,0.0009023146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9806274,"threshold_uncertainty_score":0.5561053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0805954660865807,"score_gpt":0.3016254592844599,"score_spread":0.2210299931978792,"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."}}