{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002330112,0.0007390635,0.0009415115,0.0004392819,0.0005819827,0.0007465521,0.001517039,0.001143198,0.001888505],"category_scores_gemma":[0.004767895,0.0004269101,0.0005683814,0.0006077336,0.001084895,0.001549884,0.001067095,0.001140969,0.0003424387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001187746,"about_ca_system_score_gemma":0.001569195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005653037,"about_ca_topic_score_gemma":0.003360075,"domain_scores_codex":[0.9988282,0.0004335799,0.00006852534,0.0002419633,0.0003350468,0.00009258604],"domain_scores_gemma":[0.9981432,0.001050942,0.0001995655,0.0001734841,0.0003646073,0.00006829997],"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":[0.0001126528,0.00006756805,0.0006736129,0.00008014512,0.00005095466,0.00005970529,0.00009524824,0.8804791,0.001818785,0.01594564,0.0006468719,0.09996966],"study_design_scores_gemma":[0.00001385584,0.00003326076,0.00007773613,0.000003308923,0.000004891083,0.000009624462,0.000004660615,0.9930996,0.0004211081,0.00578124,0.0005458748,0.000004804589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003345307,0.0001010212,0.9957989,0.00006022598,0.00002155695,0.00001882229,0.000004930993,0.0001235225,0.0005257005],"genre_scores_gemma":[0.6543241,0.000271326,0.3422033,0.0001491768,0.00009030524,0.000236832,0.00005714184,0.00005778025,0.002609955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005653037,"threshold_uncertainty_score":0.01232296,"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."}}