{"id":"W4246177449","doi":"10.1109/ijcnn.2006.1716100","title":"Opposition-Based Q(λ) Algorithm","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Opposition (politics); Reinforcement learning; Computer science; Lambda; Reinforcement; Artificial intelligence; Algorithm; Theoretical computer science; Engineering; Political science; Law; Physics; Structural engineering","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":[0.001871091,0.0005838658,0.001089088,0.0006862254,0.00052236,0.000697914,0.001982823,0.001316379,0.006295863],"category_scores_gemma":[0.003580891,0.0003073297,0.00044916,0.0006230646,0.0008408614,0.0009722247,0.001649462,0.001268632,0.001072353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007667515,"about_ca_system_score_gemma":0.001577348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0016383,"about_ca_topic_score_gemma":0.001576065,"domain_scores_codex":[0.9991517,0.0003261617,0.00004086837,0.0001305498,0.000231779,0.0001188828],"domain_scores_gemma":[0.9985474,0.0008493015,0.00007683672,0.00009841448,0.0003208252,0.0001072906],"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":[0.0004988302,0.0003806386,0.001097735,0.0002020146,0.0001030065,0.0001236121,0.0001840127,0.4172578,0.005851138,0.08245306,0.006318087,0.48553],"study_design_scores_gemma":[0.0001025908,0.0001331616,0.0001133735,0.00000803052,0.00001316269,0.00004156244,0.00001338926,0.9798117,0.001035898,0.01694428,0.001773905,0.000009066006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01056896,0.0001059753,0.9857101,0.0001441574,0.00004718171,0.00008988825,0.0000253614,0.0003358576,0.00297249],"genre_scores_gemma":[0.454012,0.0001471881,0.5358729,0.0004669548,0.00006481749,0.0005103963,0.0001688084,0.0001481554,0.008608689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006295863,"threshold_uncertainty_score":0.02106178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03011422955846383,"score_gpt":0.253995939575402,"score_spread":0.2238817100169381,"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."}}