{"id":"W2142097483","doi":"","title":"On Average Reward Policy Evaluation in Infinite-State Partially Observable Systems","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Observable; State space; State (computer science); Ergodic theory; Dynamical systems theory; Computer science; Q-learning; Key (lock); Dynamical system (definition); Reward system; Mathematics; Reinforcement learning; Mathematical optimization; Control theory (sociology); Artificial intelligence; Control (management); Algorithm","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":[0.008193445,0.001312586,0.002538418,0.001125108,0.0006786214,0.002270854,0.001715621,0.001941093,0.00225061],"category_scores_gemma":[0.03968749,0.0007156074,0.0007199678,0.0009954371,0.0033487,0.004042068,0.002376205,0.002355249,0.0002366799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00281415,"about_ca_system_score_gemma":0.002041502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005291469,"about_ca_topic_score_gemma":0.002743108,"domain_scores_codex":[0.9966171,0.001726654,0.0001731497,0.0005047501,0.0006151446,0.0003631928],"domain_scores_gemma":[0.9614157,0.03397165,0.00184006,0.0007217868,0.001414672,0.0006361902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001044721,0.00003783498,0.0006238546,0.00008120737,0.00003187781,0.00008469749,0.00009599359,0.9235279,0.0004887307,0.0679649,0.0002637068,0.006694758],"study_design_scores_gemma":[0.000005865201,0.00001783757,0.00008063311,0.00001081452,0.000003489639,0.000006523951,0.000006693736,0.9812558,0.0001722001,0.01837996,0.00005396574,0.000006190889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05488696,0.000640153,0.9400918,0.0008165419,0.00003599279,0.00005138814,0.00008395979,0.0001954348,0.003197717],"genre_scores_gemma":[0.9491255,0.0004998628,0.04831938,0.0001057366,0.00006778062,0.00009637317,0.000118791,0.00007893086,0.00158756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008193445,"threshold_uncertainty_score":0.04333162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02210244359152734,"score_gpt":0.2562949962152085,"score_spread":0.2341925526236811,"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."}}