{"id":"W2115615930","doi":"10.1109/ijcnn.2006.247204","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":7,"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; Task (project management); Machine learning; Engineering; 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":[0.0005769551,0.0004434439,0.0003243945,0.0002329187,0.0002863924,0.0007422955,0.001581503,0.00009628271,0.00002837776],"category_scores_gemma":[0.0000423861,0.0003556139,0.00009152617,0.0003981037,0.0001200673,0.0007089661,0.0004049499,0.000708204,0.0001113632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000523723,"about_ca_system_score_gemma":0.00004457063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000667331,"about_ca_topic_score_gemma":0.00001823154,"domain_scores_codex":[0.996664,0.00008569179,0.0007584609,0.0008330412,0.0009419912,0.0007167914],"domain_scores_gemma":[0.9988455,0.00005687819,0.0003788085,0.0003196872,0.0002503576,0.0001487388],"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":[0.00004735575,0.0001884895,0.0002709723,0.000006588221,0.0000189907,0.000006097081,0.0007351727,0.9667394,0.005350024,0.02464667,0.0003365526,0.00165373],"study_design_scores_gemma":[0.0005874382,0.0005752743,0.00231054,0.0001102389,0.000007925537,0.00001959779,0.00008739922,0.9942654,0.0004431905,0.0002070225,0.0009735784,0.0004123778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06766783,0.00001968671,0.9159742,0.002201477,0.0007406052,0.001101876,0.000001593606,0.0002153452,0.01207736],"genre_scores_gemma":[0.9810828,0.00002195453,0.01360037,0.0007853197,0.0002580521,0.0001497291,0.00003358912,0.00003289208,0.004035269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.913415,"threshold_uncertainty_score":0.9998896,"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."}}