{"id":"W1986670254","doi":"10.1115/imece2007-41644","title":"Assess Team Q-Learning Algorithm in a Purely Cooperative Multi-Robot Task","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Robot; Computer science; Task (project management); Artificial intelligence; Convergence (economics); Q-learning; Robot learning; Object (grammar); Robotics; Markov decision process; Algorithm; Machine learning; Markov process; Reinforcement learning; Mobile robot; 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":[0.00337509,0.0009166381,0.001581293,0.0005677325,0.0008000378,0.001020147,0.001740353,0.001690866,0.002816408],"category_scores_gemma":[0.006918939,0.0003920451,0.0005308312,0.0005317623,0.0009834054,0.001381204,0.001583157,0.001516459,0.0004012779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009859735,"about_ca_system_score_gemma":0.002698406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006826195,"about_ca_topic_score_gemma":0.002516512,"domain_scores_codex":[0.9986876,0.0004616087,0.00007927656,0.0003166209,0.0002481752,0.0002067011],"domain_scores_gemma":[0.9954901,0.003024006,0.0003197176,0.0001293213,0.0007891509,0.0002476721],"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":[0.0001441921,0.0000807079,0.001182368,0.00009088228,0.00004333281,0.00006695771,0.00009858125,0.933744,0.0005997585,0.008526169,0.001044999,0.05437808],"study_design_scores_gemma":[0.00002068396,0.0000397952,0.00006372337,0.000003550762,0.000005079979,0.000008142244,0.000008438542,0.9975266,0.0001183348,0.002035966,0.0001664874,0.000003190009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02255916,0.0003117422,0.9741359,0.000278646,0.00005493735,0.0001058353,0.00002177836,0.0002085793,0.002323302],"genre_scores_gemma":[0.8015011,0.0003438231,0.1932884,0.0003283243,0.00007856432,0.0004325159,0.000138513,0.00006898374,0.003819769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006826195,"threshold_uncertainty_score":0.01784939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0296036776211122,"score_gpt":0.2967484652390586,"score_spread":0.2671447876179464,"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."}}