{"id":"W2167748058","doi":"","title":"Average Reward Optimization Objective In Partially Observable Domains","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Observability; Dimension (graph theory); Observable; Representation (politics); Function (biology); Mathematics; Process (computing); Mathematical optimization; Bellman equation; Computer science; Computation; Key (lock); Applied mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001928514,0.0001025189,0.0001131869,0.00008799058,0.00006213637,0.0002433512,0.0004985115,0.00005549202,0.0003265887],"category_scores_gemma":[0.00007942965,0.00009362606,0.00002905115,0.0004007296,0.00001887661,0.001130123,0.0001975307,0.0001186697,0.0003696237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000880892,"about_ca_system_score_gemma":0.00005600605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002601806,"about_ca_topic_score_gemma":0.00003333913,"domain_scores_codex":[0.9989292,0.00006722971,0.0002314742,0.0002573265,0.0002278038,0.0002869741],"domain_scores_gemma":[0.9993126,0.00007198829,0.0000674529,0.0003995298,0.00008631862,0.00006213768],"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":[8.768976e-7,0.00001242805,0.003149157,0.000002824341,0.000004006565,0.00000312334,0.0003865356,0.9851594,0.00004770237,0.01039745,0.0004772546,0.0003592547],"study_design_scores_gemma":[0.0002517329,0.00005382023,0.006381668,0.000009563641,7.958191e-7,0.000001449812,0.00002624759,0.9919391,0.0002812502,0.0005960382,0.0003330966,0.0001251943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002340717,0.000004641643,0.9637617,0.0005445865,0.0001689571,0.0002736231,5.936817e-8,0.000165544,0.0327402],"genre_scores_gemma":[0.6458037,0.00001173362,0.348617,0.0005631411,0.00002375586,0.00003505342,0.00000270542,0.000008645811,0.004934212],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.643463,"threshold_uncertainty_score":0.4750888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01299934096471681,"score_gpt":0.2207024881727568,"score_spread":0.20770314720804,"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."}}