{"id":"W1821963137","doi":"","title":"State similarity based approach for improving performance in RL","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Similarity (geometry); Computer science; Context (archaeology); State (computer science); Artificial intelligence; Function (biology); Tree (set theory); Bellman equation; Action (physics); Machine learning; Data mining; Mathematical optimization; Algorithm; Mathematics","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":[0.001286324,0.0001023494,0.000104779,0.0001339826,0.00007719007,0.0000896705,0.00054481,0.00004335068,0.000003945939],"category_scores_gemma":[0.00005925371,0.00009383987,0.00003408222,0.0002908152,0.00002076719,0.0003948712,0.0001141078,0.0001457872,0.00000483186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007305793,"about_ca_system_score_gemma":0.00006426062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001951246,"about_ca_topic_score_gemma":0.000008149606,"domain_scores_codex":[0.9988465,0.00001394451,0.0002545383,0.0002668344,0.0002041929,0.0004139808],"domain_scores_gemma":[0.9993373,0.0001219582,0.00007116977,0.0003554607,0.00005579358,0.00005828472],"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":[0.00001188898,0.00002718459,0.01243303,0.00007531301,0.000001733674,0.000001166017,0.0001310412,0.9685346,0.0001388738,0.001717344,0.00002682934,0.01690101],"study_design_scores_gemma":[0.0004433042,0.00008963722,0.009075493,0.000004076188,9.688823e-7,6.076764e-7,0.00001154605,0.9866547,0.003107945,0.00002472353,0.0004568296,0.0001301609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008100802,0.000004004531,0.9828694,0.00005790724,0.00009575507,0.000302842,2.237115e-7,0.0001255026,0.008443494],"genre_scores_gemma":[0.5765268,4.096484e-7,0.4226845,0.0002367427,0.00001144845,0.000006942369,0.000002231348,0.000004902256,0.0005260748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.568426,"threshold_uncertainty_score":0.3826679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02225955871261686,"score_gpt":0.2490177287066525,"score_spread":0.2267581699940356,"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."}}