{"id":"W2169183587","doi":"10.1109/ijcnn.2006.246689","title":"Opposition-Based Q(λ) Algorithm","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Opposition (politics); Reinforcement learning; Computer science; Lambda; Algorithm; Artificial intelligence; Law; Political science; Physics","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":[0.00045076,0.0003544271,0.0002446093,0.0001619229,0.0003623515,0.0009686024,0.001863323,0.0001037908,0.000159143],"category_scores_gemma":[0.00004268459,0.0002764454,0.0001613324,0.0004289282,0.0001564822,0.0005539669,0.0001799852,0.0005391153,0.0005508347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001483262,"about_ca_system_score_gemma":0.00008576233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008342553,"about_ca_topic_score_gemma":0.00001156877,"domain_scores_codex":[0.9972022,0.00003873892,0.0005726708,0.0005489487,0.001050655,0.0005868021],"domain_scores_gemma":[0.998314,0.0001469185,0.0004130109,0.0003652552,0.0006596124,0.0001011691],"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":[0.00002437193,0.00007252303,0.0003368395,0.000008853822,0.00003492055,0.000005984383,0.00007129383,0.7986826,0.001931384,0.1221106,0.0715099,0.005210731],"study_design_scores_gemma":[0.0003967875,0.00009023397,0.0007526577,0.0001181092,0.00001270683,0.00003681155,0.000005925009,0.9732943,0.0008039735,0.007070878,0.01705319,0.0003643846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0102304,0.00001825438,0.9393387,0.01408788,0.002410489,0.0004209532,0.000009088803,0.0004805561,0.03300368],"genre_scores_gemma":[0.9345991,0.00001580199,0.0521987,0.003761101,0.001992154,0.00007740696,0.0000636151,0.00003874837,0.007253394],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9243687,"threshold_uncertainty_score":0.9999688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.053300843179456,"score_gpt":0.2757454530417782,"score_spread":0.2224446098623222,"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."}}