{"id":"W2284456400","doi":"10.1007/978-3-642-29946-9_21","title":"A Framework for Computing Bounds for the Return of a Policy","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Lipschitz continuity; Computer science; Piecewise; Bounding overwatch; Bounded function; Constant (computer programming); Context (archaeology); Markov decision process; Representation (politics); State (computer science); Theoretical computer science; Mathematical optimization; Markov process; Algorithm; Mathematics; Artificial intelligence; Pure 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":[0.001882456,0.0004776613,0.0005886213,0.000615978,0.0005137264,0.0004718397,0.0046795,0.0003944665,0.000004412009],"category_scores_gemma":[0.001152334,0.0003618047,0.00029834,0.000665191,0.0008485154,0.0003516424,0.001362917,0.0007660285,0.000004005563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002959117,"about_ca_system_score_gemma":0.0008421192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001906005,"about_ca_topic_score_gemma":0.00000686421,"domain_scores_codex":[0.9965582,0.00002527035,0.0007199116,0.0009008084,0.0008431032,0.0009526297],"domain_scores_gemma":[0.9908285,0.006154732,0.0007649907,0.001673543,0.0004483095,0.000129947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008801038,0.00001006184,0.00003290168,0.0001096278,0.00002648713,7.823688e-7,0.0016486,0.3489768,0.00002081447,0.3580954,0.00002261654,0.2910472],"study_design_scores_gemma":[0.0002043333,0.0002151191,0.0000352168,0.0003954352,0.00001789419,0.00001392565,3.956111e-7,0.7913996,0.00032149,0.2031053,0.003945569,0.0003457066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000004956733,0.0007150493,0.9935616,0.00186447,0.002086873,0.001243916,0.000006670901,0.00009602338,0.0004204151],"genre_scores_gemma":[0.09419462,0.00003345757,0.902409,0.001414936,0.001651974,0.00002280778,0.00000382844,0.00004685912,0.0002225503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4424228,"threshold_uncertainty_score":0.9998834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03357722234187318,"score_gpt":0.3053615565312778,"score_spread":0.2717843341894046,"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."}}