{"id":"W2051178751","doi":"10.1145/1160633.1160764","title":"Learning the required number of agents for complex tasks","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Task (project management); Computer science; Reinforcement learning; Perception; Artificial intelligence; Human–computer interaction; Machine learning; Psychology; Engineering","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":[0.001521705,0.0008133115,0.0009333502,0.0002317701,0.0004227363,0.0007502515,0.001554269,0.0008729447,0.002638479],"category_scores_gemma":[0.009985969,0.0005366144,0.0004074139,0.0001870781,0.0006461531,0.002225856,0.001048313,0.001536083,0.000487889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008086278,"about_ca_system_score_gemma":0.001687601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001595329,"about_ca_topic_score_gemma":0.002378384,"domain_scores_codex":[0.9993613,0.0001391359,0.00006582195,0.0002070825,0.0001211422,0.0001054228],"domain_scores_gemma":[0.9943537,0.002808507,0.0008159353,0.0008793045,0.0006500425,0.0004925496],"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":[0.0006263649,0.000515289,0.00412475,0.0002332097,0.00005535171,0.0001012663,0.0001546621,0.8409966,0.01957403,0.008240524,0.001044511,0.1243335],"study_design_scores_gemma":[0.00006678099,0.0001238968,0.0006289398,0.000008372525,0.000009928617,0.00003653093,0.00002701201,0.987252,0.005566763,0.005861391,0.0004080551,0.00001037595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2567295,0.0001190362,0.7391304,0.0003385445,0.00004140779,0.0001501128,0.00009223888,0.0009719302,0.002426818],"genre_scores_gemma":[0.8112982,0.00009519452,0.1865062,0.00005885552,0.00002105747,0.0002016595,0.000128775,0.0001117548,0.001578366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002638479,"threshold_uncertainty_score":0.008826613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04499630499449628,"score_gpt":0.3049986134090903,"score_spread":0.260002308414594,"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."}}