{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001097733,0.0008291429,0.0007184024,0.001407853,0.0004990694,0.000567285,0.002101219,0.0003509145,0.0000590045],"category_scores_gemma":[0.00009580055,0.0007686196,0.0001325247,0.0007685847,0.0005227739,0.0008120486,0.00169274,0.001657921,0.00004921894],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004305147,"about_ca_system_score_gemma":0.000578296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007395181,"about_ca_topic_score_gemma":0.00005803678,"domain_scores_codex":[0.9940781,0.0000818006,0.0009428716,0.00194911,0.001859563,0.001088535],"domain_scores_gemma":[0.9975377,0.0003456057,0.0006809183,0.001096809,0.0001821824,0.0001567718],"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":[0.00001930529,0.00003075158,0.00095697,0.00002893428,0.00001490667,0.0001090996,0.00216468,0.9465256,0.0004192832,0.0002571017,5.251152e-7,0.04947289],"study_design_scores_gemma":[0.001154476,0.0004862364,0.003839774,0.001530031,0.00001442098,0.00007485309,0.000002363447,0.99095,0.0001216803,0.0008490243,0.00009479853,0.0008822911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008579355,0.00005805548,0.9973629,0.00006247128,0.0003238143,0.001026235,8.374313e-7,0.0001384267,0.0001693755],"genre_scores_gemma":[0.4894556,0.00002410027,0.5101209,0.0002426309,0.00006305808,0.000008477135,0.000007209952,0.00003619186,0.00004185321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4885977,"threshold_uncertainty_score":0.9995171,"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."}}