{"id":"W7096680464","doi":"","title":"Reinforcement Learning for Factored Markov Decision Processes","year":2002,"lang":"en","type":"article","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Markov decision process; Inference; Partially observable Markov decision process; Representation (politics); Core (optical fiber); Action (physics); State (computer science); Markov process; Q-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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002135144,0.0001711691,0.0001622673,0.0001068904,0.0002444843,0.0002361787,0.000698605,0.00006694366,0.000200417],"category_scores_gemma":[0.0007816636,0.0001573173,0.00006133372,0.0003729038,0.0000253256,0.0003851004,0.0002096227,0.0001598987,0.0001756802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006986528,"about_ca_system_score_gemma":0.00003241361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000072451,"about_ca_topic_score_gemma":0.000001212952,"domain_scores_codex":[0.9985769,0.00002403961,0.0002435298,0.0003380186,0.0004151819,0.0004023162],"domain_scores_gemma":[0.9987299,0.0003967187,0.0001606552,0.0004359396,0.0001758235,0.0001009803],"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":[0.0000125496,0.00001704703,0.0003701138,0.00008018394,0.0000180023,0.000003156737,0.003593376,0.9642987,0.0001873333,0.001526564,0.007094809,0.02279822],"study_design_scores_gemma":[0.0005057729,0.0002696727,0.0001087206,0.00005323771,0.000006357262,0.000004283254,0.0001261871,0.9058011,0.001155494,0.00008729222,0.09165591,0.0002259763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001653728,0.0001279381,0.9866105,0.0005368597,0.000249913,0.0003432728,7.103854e-8,0.0003045223,0.01017322],"genre_scores_gemma":[0.8537262,0.0001078624,0.1065466,0.0001984181,0.00008122523,0.00004750776,0.000004554792,0.00002357474,0.03926408],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8800639,"threshold_uncertainty_score":0.6415212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03809663181555732,"score_gpt":0.3046626435827796,"score_spread":0.2665660117672223,"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."}}