{"id":"W2142394576","doi":"10.1109/tmech.2009.2024681","title":"Sequential $Q$-Learning With Kalman Filtering for Multirobot Cooperative Transportation","year":2009,"lang":"en","type":"article","venue":"IEEE/ASME Transactions on Mechatronics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Robot; Kalman filter; Artificial intelligence; Reinforcement learning; Sequence (biology); Table (database); Q-learning; Process (computing); Domain (mathematical analysis); Algorithm; Extended Kalman filter; Machine learning; Data mining; 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":[0.0002213099,0.000305496,0.0002578526,0.0001912079,0.0005675035,0.0001943731,0.0004680497,0.0001248341,0.00002962036],"category_scores_gemma":[0.000006828063,0.0002913788,0.0001471327,0.0003739724,0.00003588719,0.000720717,0.00000135866,0.0005238146,0.00002591138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001708964,"about_ca_system_score_gemma":0.0001293727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001004498,"about_ca_topic_score_gemma":0.00002878702,"domain_scores_codex":[0.9981296,0.00006861021,0.0003628627,0.0005307709,0.0004002568,0.0005078639],"domain_scores_gemma":[0.9990377,0.0001068489,0.0001554465,0.0004076492,0.0001695372,0.0001228445],"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":[0.000081218,0.00006634031,0.000002751907,0.00001577667,0.00004940395,0.000004479863,0.0009214664,0.9775047,0.00483125,0.006649932,0.00001403501,0.009858701],"study_design_scores_gemma":[0.001670789,0.002491234,0.00005109009,0.00007750811,0.00006398503,0.000009394436,0.0001395688,0.9591595,0.03371437,0.0001420857,0.002018095,0.0004624124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004290824,0.00001403669,0.9936252,0.0005005139,0.0003878388,0.000614823,0.00001009586,0.0004301499,0.0001264883],"genre_scores_gemma":[0.8364522,0.00002886052,0.1623672,0.0001912264,0.0000461803,0.00006590415,0.00002715587,0.00002995374,0.0007913113],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8321614,"threshold_uncertainty_score":0.9999538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01834271747908045,"score_gpt":0.257906940295863,"score_spread":0.2395642228167826,"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."}}