{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010197,0.002992193,0.003686002,0.003849189,0.001555962,0.00687465,0.006159892,0.004610756,0.007327657],"category_scores_gemma":[0.03514795,0.002458361,0.003140354,0.00343089,0.004181515,0.008012778,0.006278137,0.007742045,0.001510534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004567907,"about_ca_system_score_gemma":0.003620839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007943181,"about_ca_topic_score_gemma":0.006506902,"domain_scores_codex":[0.9942644,0.001713763,0.0004105001,0.001244433,0.001626557,0.0007403786],"domain_scores_gemma":[0.982287,0.01304312,0.0009498526,0.001831926,0.001155872,0.0007321799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002688646,0.00009813478,0.000463727,0.0001809408,0.0001256646,0.00007884562,0.0001585164,0.5966111,0.001401433,0.3121282,0.003408867,0.08507569],"study_design_scores_gemma":[0.00002390508,0.00004770752,0.00006168374,0.0000354151,0.00002670841,0.00002023395,0.00001167027,0.8337395,0.0005016048,0.1641935,0.00131211,0.00002588561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001336708,0.000280578,0.9969831,0.00009000875,0.00004255737,0.00001985075,0.00004559843,0.0003946063,0.0008070096],"genre_scores_gemma":[0.1552663,0.0008833462,0.8385074,0.0002075487,0.000328756,0.0003763441,0.0004133889,0.000534197,0.003482707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.010197,"threshold_uncertainty_score":0.05392754,"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."}}