{"id":"W2796085096","doi":"10.1007/978-3-319-89656-4_6","title":"Advice-Based Exploration in Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Social Innovation; Vector Institute; University of Toronto","funders":"","keywords":"Reinforcement learning; Satisficing; Computer science; Advice (programming); Robustness (evolution); Convergence (economics); Grid; Artificial intelligence; Operations research; Mathematical optimization; 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":[0.001560365,0.0006864014,0.0005745076,0.001761839,0.0003127887,0.0006964096,0.003207467,0.0004152479,0.00005693292],"category_scores_gemma":[0.0002122503,0.0006965353,0.0001445392,0.0009764398,0.0005841382,0.001174495,0.0008300663,0.001328871,0.000126922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008733012,"about_ca_system_score_gemma":0.001446711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001946364,"about_ca_topic_score_gemma":0.00005302458,"domain_scores_codex":[0.9947171,0.00007410724,0.0009457088,0.001637496,0.001693654,0.0009319216],"domain_scores_gemma":[0.9968217,0.0004176736,0.0006002897,0.001580781,0.0003931437,0.0001864293],"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":[0.00001160989,0.00001345179,0.0000521412,0.000045057,0.000003610395,0.00002587275,0.0006424331,0.9718223,0.00003252987,0.002132521,0.00001672147,0.02520172],"study_design_scores_gemma":[0.0006146638,0.0004171708,0.00001033233,0.0006543874,0.000005852457,0.000002583605,2.862261e-7,0.9859743,0.0008281986,0.01011986,0.0006485623,0.0007238467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002680364,0.00004952014,0.9934032,0.000592793,0.0009130557,0.0005876628,4.459913e-7,0.0003525908,0.004073916],"genre_scores_gemma":[0.3560344,0.00001525568,0.6397424,0.002464481,0.0003089144,0.00003642891,0.00003155017,0.00007093279,0.001295569],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3560076,"threshold_uncertainty_score":0.9995486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02666271158748201,"score_gpt":0.2551386000725917,"score_spread":0.2284758884851097,"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."}}