{"id":"W2081239738","doi":"10.1109/adprl.2007.368191","title":"Opposition-Based Reinforcement Learning in the Management of Water Resources","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Exploit; Bellman equation; Opposition (politics); Artificial intelligence; Action learning; Operations research; Mathematical optimization; Engineering; Computer security; Mathematics; Law; Political science; Cooperative learning","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":[0.001699047,0.00009792598,0.00009168841,0.0001557685,0.00009052708,0.00007627896,0.0008315857,0.00003113602,0.00005163805],"category_scores_gemma":[0.000004667862,0.00005749933,0.00004554728,0.0002778239,0.00003481481,0.0001392696,0.0001641161,0.0001504924,0.00003761972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003829459,"about_ca_system_score_gemma":0.000006249881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002973771,"about_ca_topic_score_gemma":0.000002663221,"domain_scores_codex":[0.998569,0.00005861246,0.0003641137,0.0001718256,0.0005182142,0.0003182952],"domain_scores_gemma":[0.9993427,0.0001058604,0.00007520435,0.0004123402,0.00003548228,0.00002842514],"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":[0.000007204739,0.00001682899,0.0007763999,0.00003490867,0.00001284902,0.00002238658,0.001817629,0.9774881,0.0002765337,0.01769909,0.00003554042,0.001812533],"study_design_scores_gemma":[0.0009884123,0.0003532261,0.006959757,0.0001308041,0.00001512814,0.000003975166,0.001347745,0.9486541,0.02644317,0.0001754433,0.01465911,0.0002690987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01602907,0.00000623655,0.9231679,0.000597233,0.00005564326,0.0001957093,1.261612e-8,0.00006137387,0.05988678],"genre_scores_gemma":[0.9754455,0.000003083844,0.02235682,0.0005278887,0.00001132028,0.000006694106,0.000003318748,0.000004666388,0.001640705],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9594164,"threshold_uncertainty_score":0.2344755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01448153100697104,"score_gpt":0.2446827248964791,"score_spread":0.230201193889508,"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."}}