{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001918835,0.0005443676,0.0008676007,0.0005875477,0.0004893452,0.0006725352,0.002012045,0.0013266,0.009186946],"category_scores_gemma":[0.004323493,0.0002573396,0.0003865298,0.0005563585,0.000967645,0.001072912,0.001689367,0.001282115,0.001436576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006862875,"about_ca_system_score_gemma":0.001358829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001492782,"about_ca_topic_score_gemma":0.001450769,"domain_scores_codex":[0.9991668,0.0003240673,0.00004328111,0.0001176045,0.0002355456,0.0001126751],"domain_scores_gemma":[0.9984065,0.000926186,0.00008026338,0.0001156401,0.0003565862,0.0001149443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005996911,0.0003515131,0.001153429,0.0002060871,0.00007919999,0.0001513971,0.0001964984,0.2938714,0.004724749,0.09735903,0.009455307,0.5918517],"study_design_scores_gemma":[0.0001236991,0.000176145,0.00013951,0.00001009228,0.00001405594,0.00006319021,0.0000171543,0.9689229,0.001504567,0.02603993,0.002977489,0.0000112569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008835741,0.00009012158,0.9861985,0.0001809206,0.00005573844,0.00009669916,0.00003436681,0.0004735414,0.004034367],"genre_scores_gemma":[0.4422873,0.0001238603,0.5466424,0.000462459,0.00007213229,0.0004906067,0.0001653154,0.0001507898,0.009605201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009186946,"threshold_uncertainty_score":0.03073341,"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."}}