{"id":"W1569513695","doi":"10.1007/978-3-540-24840-8_30","title":"Multi-attribute Decision Making in a Complex Multiagent Environment Using Reinforcement Learning with Selective Perception","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Perception; Artificial intelligence; Machine learning; Human–computer interaction","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":[0.001940456,0.0006290954,0.001056602,0.0002783126,0.0004729955,0.001118171,0.001273468,0.0009371646,0.001492456],"category_scores_gemma":[0.004299837,0.000471988,0.0006778014,0.0003962986,0.001076466,0.001540647,0.0013533,0.001590918,0.0001561102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007486199,"about_ca_system_score_gemma":0.0007400093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002728927,"about_ca_topic_score_gemma":0.002511794,"domain_scores_codex":[0.9993401,0.0002741799,0.00004123724,0.0001270287,0.0001536325,0.00006380995],"domain_scores_gemma":[0.9971909,0.002024846,0.000199126,0.0001660737,0.0002442734,0.0001748249],"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":[0.0001966154,0.0002049362,0.001321082,0.00007110539,0.0001311589,0.0001460625,0.0002039965,0.915617,0.004196833,0.01608423,0.0006060134,0.06122087],"study_design_scores_gemma":[0.0000126093,0.00002838411,0.0001051226,0.00000311309,0.000009525411,0.00001119434,0.00000823925,0.993067,0.0004386274,0.006236064,0.00007498507,0.000005133167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0777959,0.0001437408,0.9196641,0.0001993211,0.00003884814,0.00005764701,0.00001689041,0.0002076271,0.001875892],"genre_scores_gemma":[0.8469521,0.0001052371,0.1515146,0.0000594824,0.00002622328,0.000112983,0.00002586161,0.00002828397,0.001175145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002728927,"threshold_uncertainty_score":0.01026225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03624636363657711,"score_gpt":0.2758972560173434,"score_spread":0.2396508923807663,"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."}}