{"id":"W4250455569","doi":"10.1109/ijcnn.2006.1716795","title":"Extend Single-agent Reinforcement Learning Approach to a Multi-robot Cooperative Task in an Unknown Dynamic Environment","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","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":"Reinforcement learning; Computer science; Robot; Markov decision process; Robustness (evolution); Robot learning; Artificial intelligence; Q-learning; Obstacle; Mobile robot; Markov process; Machine learning; 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":[0.0009824346,0.0006061138,0.0007484176,0.000219114,0.0003270694,0.0004071254,0.0009693963,0.0007411573,0.001382737],"category_scores_gemma":[0.001574774,0.0002174507,0.0005756582,0.0002223568,0.0007291179,0.0008762276,0.0007644165,0.0009221503,0.0002511123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004123751,"about_ca_system_score_gemma":0.0008313606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002115722,"about_ca_topic_score_gemma":0.001210599,"domain_scores_codex":[0.9996356,0.0001350444,0.00002068958,0.00008474714,0.00008204321,0.00004187114],"domain_scores_gemma":[0.9992691,0.0004114909,0.00007389131,0.00007568442,0.0001163134,0.00005364025],"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":[0.00004661958,0.00008590785,0.0007491327,0.0000818676,0.00005005211,0.0002233949,0.0001013247,0.9375379,0.004082713,0.01402032,0.0004004096,0.04262038],"study_design_scores_gemma":[0.000009644513,0.00003518985,0.00005799393,0.000002216269,0.000004847277,0.00001964441,0.000004276373,0.99501,0.0004517614,0.004001485,0.0003993835,0.000003429055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01631344,0.0001191528,0.9818392,0.0001725533,0.000033178,0.00003625384,0.000009320058,0.0001528147,0.001324021],"genre_scores_gemma":[0.8544557,0.0002320707,0.1424401,0.0001464443,0.00004193036,0.0001422386,0.00003043408,0.00002877805,0.002482333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002115722,"threshold_uncertainty_score":0.005195677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05280801083795682,"score_gpt":0.2672504729988086,"score_spread":0.2144424621608517,"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."}}