{"id":"W2496219042","doi":"10.4018/978-1-60960-171-3.ch007","title":"Reward Shaping and Mixed Resolution Function Approximation","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Representation (politics); Function approximation; Function (biology); Reinforcement learning; Computer science; Space (punctuation); Core (optical fiber); Resolution (logic); Function space; Artificial intelligence; Quality (philosophy); Process (computing); Algorithm; Mathematics; Artificial neural network; Discrete 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001489113,0.0009990908,0.0009426008,0.0005219852,0.0003197912,0.001726828,0.001544697,0.001677234,0.006046676],"category_scores_gemma":[0.004967592,0.0005117081,0.0008874924,0.0006578217,0.001439005,0.001862358,0.001623189,0.002620343,0.001300006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001390446,"about_ca_system_score_gemma":0.0007392453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009212453,"about_ca_topic_score_gemma":0.0006837809,"domain_scores_codex":[0.999198,0.0003228734,0.00003457545,0.0001302654,0.0002422956,0.00007203262],"domain_scores_gemma":[0.9986986,0.0008981166,0.00009354261,0.0001334866,0.0001184864,0.00005769707],"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":[0.0001345654,0.00007742043,0.0003107874,0.0002529724,0.0000483734,0.0001325027,0.0001788449,0.5110839,0.004575997,0.3010006,0.003090342,0.1791137],"study_design_scores_gemma":[0.00001198158,0.00005038506,0.00006568168,0.00004609166,0.00001089544,0.00006035221,0.00001107644,0.929436,0.001299404,0.06476769,0.004227578,0.00001285686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003194719,0.0007723155,0.9886098,0.0001903332,0.00003842803,0.00002591378,0.00001383868,0.0002376614,0.006917083],"genre_scores_gemma":[0.3828178,0.001942725,0.5895984,0.0003219336,0.0001139969,0.000296977,0.0001027721,0.0002933677,0.02451203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006046676,"threshold_uncertainty_score":0.02022815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04342473939920324,"score_gpt":0.2337610620735649,"score_spread":0.1903363226743616,"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."}}