{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002455873,0.0003210068,0.0002696944,0.000104187,0.0001672713,0.0002045526,0.000425782,0.0003766514,0.000009475409],"category_scores_gemma":[0.0000256717,0.0003416543,0.00009224607,0.00002501863,0.0000779241,0.0002299842,0.0003793481,0.0002869537,0.0001455547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002230869,"about_ca_system_score_gemma":0.00008362503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002658796,"about_ca_topic_score_gemma":0.000007253109,"domain_scores_codex":[0.9983207,0.00002951831,0.0003874103,0.0005571847,0.0004215014,0.0002836947],"domain_scores_gemma":[0.9987586,0.0000223625,0.0003772655,0.0006082354,0.0001254344,0.0001081217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001501594,0.000001698323,0.000007076037,0.00004183278,0.0000371301,0.000005056201,0.00008276875,0.0008771785,0.000009423378,0.9819344,0.0006707133,0.01631777],"study_design_scores_gemma":[0.0006234776,0.0004777921,0.000384695,0.0005721301,0.0001387514,0.00008237946,0.000007847912,0.06726377,0.0000537333,0.8802115,0.04915341,0.001030464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.000008886765,0.0001109229,0.4879559,0.00001916221,0.0004972426,0.0001821656,0.000001663224,0.0001960267,0.511028],"genre_scores_gemma":[0.4574714,0.00009511531,0.125353,0.001806959,0.001484949,0.00008730422,0.00006199339,0.000230138,0.4134091],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4574625,"threshold_uncertainty_score":0.9999036,"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."}}