{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072665,0.0003748134,0.0003739524,0.0002639217,0.000655353,0.0006429353,0.000762779,0.0001634604,0.000008847484],"category_scores_gemma":[0.0002019615,0.0003414323,0.0001251228,0.0002515775,0.00005588511,0.0008118253,0.0005037243,0.0004893672,0.00004698865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009004336,"about_ca_system_score_gemma":0.0001047327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005621783,"about_ca_topic_score_gemma":0.000005915185,"domain_scores_codex":[0.9973838,0.00009431536,0.0005935272,0.0006824409,0.0005060001,0.0007399363],"domain_scores_gemma":[0.9983873,0.0001413403,0.0004104633,0.0005359778,0.0002184811,0.0003063809],"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":[0.00002124426,0.00007026424,0.001339009,0.00009151302,0.0002252631,0.00001811232,0.003370405,0.9617352,0.002095703,0.01786132,0.0004684745,0.01270345],"study_design_scores_gemma":[0.001594601,0.0002906306,0.001124516,0.00008843073,0.00002096011,0.00002360533,0.0003784449,0.9735807,0.0001502521,0.000009275698,0.02235008,0.0003884586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01375788,0.00008064912,0.9821928,0.000116347,0.001683894,0.001191839,0.000002751896,0.0001990298,0.0007748594],"genre_scores_gemma":[0.918988,0.00006690561,0.07539506,0.0001797037,0.0003784862,0.0001383453,0.0000158374,0.00004316452,0.004794449],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9067977,"threshold_uncertainty_score":0.9999038,"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."}}