{"id":"W1561485809","doi":"10.1007/978-3-540-70829-2_11","title":"The Concept of Opposition and Its Use in Q-Learning and Q(λ) Techniques","year":2008,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Opposition (politics); Q-learning; Artificial intelligence; TRACE (psycholinguistics); Mathematical optimization; Mathematics","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":[0.0002912917,0.0001920504,0.0002787466,0.0001855194,0.0001600033,0.00005543464,0.0002761236,0.00009187419,0.000001392037],"category_scores_gemma":[0.0002978515,0.0001651701,0.00002805038,0.00008814631,0.0005344695,0.0002311514,0.0005346089,0.0004065068,0.000001843582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007664217,"about_ca_system_score_gemma":0.0000464987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007299547,"about_ca_topic_score_gemma":0.000009995042,"domain_scores_codex":[0.9986583,0.00005547467,0.0005109655,0.0003180098,0.0003099129,0.0001473099],"domain_scores_gemma":[0.9972669,0.002012299,0.0002823081,0.000112713,0.0003023483,0.00002344276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007976108,0.000005196703,0.000189536,0.00004720443,0.00004705833,0.00002641313,0.002572936,0.4594203,0.000002140034,0.5194147,0.00007412815,0.01819246],"study_design_scores_gemma":[0.0002358542,0.0007030035,0.0006020588,0.002919838,0.0000223635,0.0001588562,0.0005748824,0.8700594,0.00075257,0.1059536,0.01706005,0.0009575416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006300887,0.02972743,0.9514805,0.0005610095,0.0004447507,0.001017126,0.000005762752,0.0001312537,0.01600208],"genre_scores_gemma":[0.8295595,0.07511276,0.07280128,0.0001805794,0.00009534007,0.0000496981,0.00001867475,0.00005195076,0.0221302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8786792,"threshold_uncertainty_score":0.6735442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09245566855671966,"score_gpt":0.3442205430760504,"score_spread":0.2517648745193307,"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."}}