{"id":"W2011033111","doi":"10.1109/adprl.2007.368201","title":"Opposition-Based Q(λ) with Non-Markovian Update","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Opposition (politics); Computer science; Markov process; Algorithm; Theoretical computer science; Statistical physics; Mathematics; Physics; Law; Statistics","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":[0.0004554967,0.000158202,0.0001228589,0.0001550431,0.0001541543,0.0002112411,0.0007283388,0.00005523854,0.0001442542],"category_scores_gemma":[0.00001833169,0.0001252598,0.00004237454,0.0004931054,0.00005426115,0.0003535411,0.0000953108,0.0001574555,0.000503414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005871759,"about_ca_system_score_gemma":0.00009883947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003056196,"about_ca_topic_score_gemma":0.00004210229,"domain_scores_codex":[0.9985825,0.00002070218,0.0002303836,0.0003141383,0.000425906,0.0004263484],"domain_scores_gemma":[0.9987864,0.0001233657,0.00008951632,0.0007217833,0.0001137751,0.0001651182],"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":[0.00004915352,0.0001044943,0.007727143,0.00003579782,0.00005700133,0.00005977849,0.0003086355,0.9344596,0.001743709,0.03864873,0.007093958,0.009711982],"study_design_scores_gemma":[0.00166769,0.0005099843,0.007299663,0.00008848716,0.00002295065,0.00003649883,0.00004003585,0.9068146,0.009162733,0.0002107768,0.07325622,0.0008903036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002045406,0.000003593253,0.9519098,0.0009151564,0.0002034475,0.0001471487,2.642384e-7,0.0002736484,0.04450152],"genre_scores_gemma":[0.5183142,8.913318e-7,0.4770013,0.002296231,0.00005425663,0.000003615223,0.0000103952,0.00001239848,0.002306765],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5162688,"threshold_uncertainty_score":0.6470536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009002528772758794,"score_gpt":0.2387725281728582,"score_spread":0.2297699994000994,"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."}}