{"id":"W126702457","doi":"10.1007/978-3-662-45355-1_11","title":"Reinforcement Learning Using Monte Carlo Policy Estimation for Disaster Mitigation","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Infrastructure Resilience and Vulnerability Analysis","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Reinforcement learning; Novelty; Exploit; Interdependence; Risk analysis (engineering); Monte Carlo method; Critical infrastructure; Operations research; Artificial intelligence; Computer security","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":[0.001568611,0.0009477477,0.0009730851,0.000466865,0.0002960991,0.0009568485,0.001092967,0.001261818,0.002911626],"category_scores_gemma":[0.007285952,0.0004939283,0.0005341333,0.0006800409,0.001037615,0.0008723247,0.0008147621,0.001945297,0.000448444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001417645,"about_ca_system_score_gemma":0.00118564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007424468,"about_ca_topic_score_gemma":0.005013261,"domain_scores_codex":[0.9993448,0.0003862914,0.00002382973,0.00008417122,0.0001192832,0.00004166524],"domain_scores_gemma":[0.9959117,0.003600064,0.0001633662,0.00008828758,0.0001764529,0.0000601479],"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":[0.00002938815,0.00002372327,0.0002313096,0.00003386051,0.00002290513,0.00001645408,0.00001811631,0.9744154,0.0001366858,0.007084514,0.0005068197,0.01748084],"study_design_scores_gemma":[0.000003478375,0.000006870815,0.00002903041,0.000004922278,0.000002223465,0.000003083528,0.000001457214,0.9949049,0.00006664482,0.004720507,0.0002543623,0.000002531564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009358237,0.002134821,0.9816537,0.0004753991,0.0001010356,0.00004440905,0.00003656122,0.0004172475,0.005778631],"genre_scores_gemma":[0.7042497,0.002988081,0.282835,0.0003207191,0.0002403287,0.0004008343,0.0001884506,0.0001799186,0.008596913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007424468,"threshold_uncertainty_score":0.01476252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009906396779310466,"score_gpt":0.2486138352939954,"score_spread":0.238707438514685,"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."}}