{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005498489,0.0002306714,0.0002937219,0.0004271247,0.0002118487,0.0002999356,0.0006300904,0.00007062213,0.00002680802],"category_scores_gemma":[0.0001218115,0.0002071642,0.0001410916,0.0004091804,0.00009627332,0.001508154,0.0001231656,0.0004298322,0.00003695668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001333639,"about_ca_system_score_gemma":0.0001893375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003933322,"about_ca_topic_score_gemma":3.057756e-7,"domain_scores_codex":[0.9970205,0.00004714569,0.001684827,0.0001173148,0.0008316338,0.0002985694],"domain_scores_gemma":[0.9971184,0.0004653713,0.001237984,0.0001822251,0.0008631263,0.0001329653],"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":[0.0000166519,0.00003243827,0.0001371404,0.00004180925,0.00002345207,0.000006417903,0.0004112443,0.9284414,0.00002472308,0.05218075,0.0001128595,0.01857112],"study_design_scores_gemma":[0.0001901074,0.0006821066,0.0000877072,0.0001478156,0.00001389779,0.00009786877,0.000423391,0.9779323,0.003763405,0.01207858,0.004354897,0.0002279639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002484691,0.0001775767,0.9947917,0.0002583821,0.0003203919,0.0001457123,3.951245e-7,0.00005071062,0.00177046],"genre_scores_gemma":[0.712014,0.000119827,0.2872182,0.0004158129,0.00006795237,0.000002784506,0.0000132802,0.000009202067,0.0001388741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7095293,"threshold_uncertainty_score":0.8447911,"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."}}