{"id":"W190427941","doi":"10.20965/jaciii.2006.p0578","title":"Opposition-Based Reinforcement Learning","year":2006,"lang":"en","type":"article","venue":"Journal of Advanced Computational Intelligence and Intelligent Informatics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":207,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Expediting; Artificial intelligence; A priori and a posteriori; Probabilistic logic; Grid; Machine learning; Opposition (politics); Convergence (economics); Learning classifier system; Engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001305042,0.0007572739,0.00137536,0.0004510494,0.0003827406,0.0007528921,0.001312855,0.0009079622,0.002439095],"category_scores_gemma":[0.004146397,0.0002634005,0.0004754123,0.000427672,0.001189939,0.0007089592,0.001078284,0.001154256,0.0003888851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006690928,"about_ca_system_score_gemma":0.000776189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002104882,"about_ca_topic_score_gemma":0.001569994,"domain_scores_codex":[0.9992041,0.0003349317,0.00004108679,0.0001116092,0.0002251142,0.00008315192],"domain_scores_gemma":[0.9983249,0.001059433,0.0001702817,0.0001012262,0.0002536059,0.00009047782],"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":[0.0001603872,0.0001495115,0.0009686153,0.0001532397,0.00009311277,0.0001595781,0.00009601682,0.8630928,0.002227417,0.03708625,0.001675329,0.09413773],"study_design_scores_gemma":[0.00004206536,0.00008306065,0.00008467263,0.000009052339,0.000009039812,0.00003193262,0.000006294493,0.9886839,0.0004722035,0.009446564,0.001123047,0.000008128266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01372192,0.0002728781,0.9801165,0.000162988,0.00006880312,0.00009176248,0.00002580292,0.0003130999,0.005226076],"genre_scores_gemma":[0.8651396,0.0003277849,0.129491,0.0002459216,0.00005394258,0.0003617169,0.00008603418,0.00004789277,0.004246194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002439095,"threshold_uncertainty_score":0.008159518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01614136464924268,"score_gpt":0.2628008458279594,"score_spread":0.2466594811787167,"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."}}