{"id":"W1986670254","doi":"10.1115/imece2007-41644","title":"Assess Team Q-Learning Algorithm in a Purely Cooperative Multi-Robot Task","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; Task (project management); Artificial intelligence; Convergence (economics); Q-learning; Robot learning; Object (grammar); Robotics; Markov decision process; Algorithm; Machine learning; Markov process; Reinforcement learning; Mobile robot; Engineering","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":[0.001224179,0.0002147989,0.0002318682,0.0002685937,0.0001569853,0.0002713774,0.0008322789,0.0001177672,0.00004058949],"category_scores_gemma":[0.0002517762,0.0001949701,0.00005197702,0.0008619176,0.00005469442,0.0006776808,0.0003697567,0.0006419562,0.0002186654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001465463,"about_ca_system_score_gemma":0.00009832773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001083149,"about_ca_topic_score_gemma":0.00005699336,"domain_scores_codex":[0.997932,0.0001240671,0.0004416932,0.0004686237,0.0004269025,0.0006067253],"domain_scores_gemma":[0.9989207,0.0002781387,0.0001249942,0.0003873537,0.0001524132,0.0001363642],"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":[0.000004672367,0.000108868,0.007272573,0.000008189699,0.00002316481,0.00009978534,0.001959746,0.9401547,0.001138825,0.008193345,0.0003481626,0.04068793],"study_design_scores_gemma":[0.0007137965,0.0001572238,0.009957734,0.00002584894,0.000002403166,0.00001570274,0.0002825187,0.9827801,0.001296874,0.00001423764,0.004471004,0.0002825715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006152568,0.00002623227,0.9837431,0.0001348297,0.0002965388,0.0002488251,1.969958e-7,0.0003105845,0.01462439],"genre_scores_gemma":[0.3493569,0.00001007535,0.6415346,0.0003887725,0.00005031076,0.000009009825,0.000004758781,0.00001816791,0.008627364],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3487417,"threshold_uncertainty_score":0.7950649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0296036776211122,"score_gpt":0.2967484652390586,"score_spread":0.2671447876179464,"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."}}