{"id":"W2158304715","doi":"10.1109/tsmcb.2007.899419","title":"Positive Impact of State Similarity on Reinforcement Learning Performance","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Similarity (geometry); Artificial intelligence; Context (archaeology); Computer science; Reinforcement; Function (biology); Bellman equation; Tree (set theory); State (computer science); Action (physics); Machine learning; Value (mathematics); Mathematics; Mathematical optimization; Algorithm; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009430451,0.0004864989,0.0005156912,0.0003898934,0.0003392026,0.0002236282,0.0005581081,0.000190839,0.00002964814],"category_scores_gemma":[0.00001448623,0.0004565993,0.0002166781,0.0004509721,0.0001997549,0.0002541568,0.00001996002,0.0007678471,0.00008493297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002619226,"about_ca_system_score_gemma":0.00009039092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002517634,"about_ca_topic_score_gemma":0.00001764647,"domain_scores_codex":[0.9965585,0.0001673737,0.0009763135,0.0006164482,0.0009184342,0.000762912],"domain_scores_gemma":[0.9977781,0.0003650051,0.0004859903,0.0007690185,0.0002644689,0.0003373898],"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":[0.0001093308,0.0001165055,0.0007265596,0.0000794779,0.0001652709,0.00001284012,0.001455078,0.9901695,0.0003239034,0.000976034,0.00009522978,0.00577028],"study_design_scores_gemma":[0.001666673,0.005781939,0.01106102,0.0006560808,0.00009112738,0.0000602127,0.0001862359,0.9583239,0.0195062,0.00003495403,0.001709909,0.0009217653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2074239,0.00005768205,0.7840869,0.00003009033,0.0006713541,0.0005375838,0.000007870045,0.0001374399,0.007047214],"genre_scores_gemma":[0.992153,0.0003624199,0.0005845778,0.0000690491,0.00005870287,0.00001681199,0.000006093185,0.00004396878,0.00670539],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7847291,"threshold_uncertainty_score":0.9997886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01715931351416537,"score_gpt":0.2565818502936981,"score_spread":0.2394225367795328,"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."}}