{"id":"W2151620419","doi":"10.1111/coin.12016","title":"EFFICIENT ABSTRACTION SELECTION IN REINFORCEMENT LEARNING","year":2013,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Abstraction; Markov decision process; Action selection; Selection (genetic algorithm); Context (archaeology); Artificial intelligence; Set (abstract data type); Machine learning; State space; Class (philosophy); Theoretical computer science; Markov process; Programming language; Mathematics; Agency (philosophy)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002628168,0.0001311871,0.0001051841,0.000248718,0.0001334875,0.0002068463,0.0003778057,0.00005319104,0.0001949292],"category_scores_gemma":[0.0001112455,0.0001389468,0.00003319366,0.0005995125,0.0000327411,0.0003306111,0.0001145156,0.0003145914,0.001187821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002036024,"about_ca_system_score_gemma":0.00006746529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001006025,"about_ca_topic_score_gemma":0.000001879299,"domain_scores_codex":[0.9985027,0.00005782307,0.0004241246,0.0003091645,0.0004336165,0.0002726099],"domain_scores_gemma":[0.9992269,0.0002201459,0.0001554489,0.0001096667,0.000221166,0.00006666577],"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":[0.000001456734,0.00001925004,0.000683996,0.000006718573,0.000004422254,0.000001201673,0.0003000528,0.9697675,0.0001172439,0.02018131,0.00004969171,0.008867132],"study_design_scores_gemma":[0.00005747757,0.00008520791,0.013368,0.00002455254,0.000001016204,0.00001049316,0.00004757371,0.9829576,0.0003533816,0.002799134,0.0001507543,0.0001447819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01701595,0.00001473206,0.9795288,0.0002331844,0.0001990311,0.0002583573,2.602871e-8,0.0001543412,0.002595602],"genre_scores_gemma":[0.9560931,0.000004122202,0.04320315,0.0001177766,0.00003062712,0.00003614579,0.000004971205,0.00000721583,0.000502901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9390771,"threshold_uncertainty_score":0.9995899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02106858788774564,"score_gpt":0.2715625062281282,"score_spread":0.2504939183403826,"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."}}