{"id":"W1985646234","doi":"10.1115/imece2007-41643","title":"A Modified Q-Learning Algorithm for Multi-Robot Decision Making","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; Q-learning; Markov decision process; Artificial intelligence; Algorithm; Kalman filter; Robot learning; Domain (mathematical analysis); Markov chain; Reinforcement learning; Markov process; Machine learning; Mobile robot; 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":[],"consensus_categories":[],"category_scores_codex":[0.001130479,0.0001622344,0.0001627255,0.0001922111,0.0002712812,0.0002279982,0.0007630908,0.00009550472,0.00001594641],"category_scores_gemma":[0.000287326,0.0001479643,0.00009942487,0.000331232,0.00002304536,0.0003743947,0.0003030816,0.0002139226,0.00006073111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007452298,"about_ca_system_score_gemma":0.00003135299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000618667,"about_ca_topic_score_gemma":0.000003487421,"domain_scores_codex":[0.9983152,0.00002369428,0.0003739045,0.0003973404,0.0003605632,0.000529326],"domain_scores_gemma":[0.9986123,0.0006194846,0.0001392009,0.0003952368,0.000141434,0.00009233995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005294406,0.00001442322,0.0001068776,0.000004153146,0.000008530698,0.000006030096,0.0001824976,0.4604966,0.00008557495,0.006764994,0.00009221432,0.5322328],"study_design_scores_gemma":[0.0006523587,0.0001118937,0.0008210472,0.00003556375,0.000004016548,0.000009071255,0.00004407658,0.9951027,0.0003697084,0.0002452118,0.002400146,0.0002041863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001780578,0.00002014371,0.9959292,0.00003532216,0.0004802162,0.0003024829,1.760862e-7,0.0004241226,0.002630235],"genre_scores_gemma":[0.1477857,0.0000025958,0.8497532,0.0002295325,0.00006806726,0.000007943666,0.000001764063,0.00001649952,0.00213466],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5346061,"threshold_uncertainty_score":0.6033809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05076914814580656,"score_gpt":0.3375238673067552,"score_spread":0.2867547191609486,"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."}}