{"id":"W189510620","doi":"10.5555/1838206.1838300","title":"Optimal policy switching algorithms for reinforcement learning","year":2010,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Function approximation; Term (time); Function (biology); Artificial intelligence; Mathematical optimization; Q-learning; Machine learning; Algorithm; Mathematics; Artificial neural network; 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":[0.002082137,0.001189238,0.001465055,0.00079528,0.0004419448,0.001030006,0.001571678,0.001459509,0.004694636],"category_scores_gemma":[0.007191912,0.0005578952,0.0005727783,0.0007114283,0.001409854,0.001326414,0.001395877,0.002507455,0.0006836968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001451451,"about_ca_system_score_gemma":0.001414925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003093485,"about_ca_topic_score_gemma":0.00223926,"domain_scores_codex":[0.9990702,0.0004071347,0.00005326107,0.0001511677,0.0002208646,0.00009743308],"domain_scores_gemma":[0.9972885,0.002113807,0.0001654905,0.0001094786,0.000226448,0.00009628199],"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":[0.00008640675,0.0000929384,0.0003283193,0.00008829762,0.00004141103,0.00003113308,0.00006943924,0.8635923,0.0004243212,0.06594282,0.001609219,0.06769338],"study_design_scores_gemma":[0.0000204624,0.00001671238,0.00002193217,0.000006901428,0.000003713704,0.000004511725,0.00000350216,0.9754724,0.0001134768,0.02394746,0.0003851832,0.000003639451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005134111,0.0004003887,0.991503,0.0001692707,0.00004741728,0.0000595657,0.00002647261,0.0003059002,0.002353836],"genre_scores_gemma":[0.5969837,0.0008321248,0.3954748,0.0003412707,0.0001306455,0.0008130967,0.0002143644,0.0001987935,0.005011176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004694636,"threshold_uncertainty_score":0.01570511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05548713756434804,"score_gpt":0.3163627497273219,"score_spread":0.2608756121629739,"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."}}