{"id":"W1801772197","doi":"10.1007/978-3-540-72665-4_5","title":"R-FRTDP: A Real-Time DP Algorithm with Tight Bounds for a Stochastic Resource Allocation Problem","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Markov decision process; Mathematical optimization; Resource allocation; Heuristic; Context (archaeology); Task (project management); Stochastic programming; Dynamic programming; Resource (disambiguation); Markov process; Algorithm; Artificial intelligence; 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":[0.001675935,0.000742753,0.0006537953,0.001114509,0.0004790421,0.0009219185,0.003423468,0.0004239415,0.00001387208],"category_scores_gemma":[0.00008885818,0.0006446521,0.000136848,0.0009140861,0.0008008597,0.0006383514,0.0008520986,0.0008147144,0.00005228175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006210286,"about_ca_system_score_gemma":0.000931589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002293502,"about_ca_topic_score_gemma":0.00002232104,"domain_scores_codex":[0.9945735,0.00003542148,0.0007516339,0.001872762,0.001650336,0.001116356],"domain_scores_gemma":[0.9959322,0.0009219851,0.0006317957,0.001693777,0.0005599385,0.0002603132],"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":[0.00001750946,0.00001818572,0.00000194429,0.00005109786,0.00002245341,0.00002562385,0.0006996398,0.7431248,0.00004967585,0.008424956,0.00006233403,0.2475017],"study_design_scores_gemma":[0.0005431515,0.0008431278,0.000011296,0.0006402226,0.00002423996,0.00009676333,2.490337e-7,0.9802047,0.0001554179,0.01252767,0.00413013,0.0008230287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003576082,0.00007033876,0.9913605,0.0004954741,0.0004254519,0.001443167,0.000004317923,0.0003501799,0.005846979],"genre_scores_gemma":[0.001287477,0.000008406224,0.993207,0.0007003901,0.0004942828,0.00004591491,0.00003430442,0.00008347569,0.004138723],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2466787,"threshold_uncertainty_score":0.9996005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147342081768551,"score_gpt":0.2464556985615334,"score_spread":0.2317214903846783,"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."}}