{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002369784,0.0009282783,0.001399091,0.0004575882,0.0004760937,0.0007760549,0.0009923677,0.001062804,0.001364263],"category_scores_gemma":[0.007079072,0.0005113739,0.0005167865,0.0004097031,0.001761338,0.001628885,0.001803311,0.001383372,0.0001809389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001207291,"about_ca_system_score_gemma":0.001254297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002182231,"about_ca_topic_score_gemma":0.001780608,"domain_scores_codex":[0.9985759,0.0007169156,0.00006198612,0.0002288784,0.0002465448,0.0001697155],"domain_scores_gemma":[0.9973598,0.001871929,0.0002685065,0.0002053336,0.0001554654,0.0001389663],"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":[0.0001058489,0.00005340447,0.0008815315,0.00006169309,0.00003889273,0.00007041125,0.00008708554,0.9473156,0.001000675,0.02693757,0.0003175611,0.02312983],"study_design_scores_gemma":[0.00002502424,0.00003607972,0.00007367755,0.000007108204,0.000008438722,0.000009686509,0.000009375013,0.9799296,0.0004051953,0.01925352,0.0002377506,0.000004608445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07159132,0.000342628,0.9252955,0.0002587745,0.00002260805,0.00009772843,0.00003541927,0.0002570228,0.002099025],"genre_scores_gemma":[0.9062374,0.0001688443,0.09230384,0.00007420995,0.00002073645,0.000168853,0.00005637568,0.00003275269,0.0009369577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002369784,"threshold_uncertainty_score":0.01253271,"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."}}