{"id":"W3210485068","doi":"10.1613/jair.1.13445","title":"Multi-Agent Advisor Q-Learning","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Government of Canada; Vector Institute; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Artificial intelligence; Action (physics); Heuristic; Sample complexity; Software deployment; Convergence (economics); Point (geometry); Operations research; Machine learning; Q-learning; Software engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008302711,0.000121712,0.0002266124,0.0008439944,0.001029574,0.0003633553,0.002497504,0.00004174643,0.0004721413],"category_scores_gemma":[0.001429106,0.0001150427,0.0001663139,0.001580966,0.0001350596,0.0004877992,0.001303754,0.002512945,0.0002042301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00038629,"about_ca_system_score_gemma":0.0004528772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002254862,"about_ca_topic_score_gemma":0.000001874601,"domain_scores_codex":[0.994603,0.001129965,0.0008810347,0.0002612244,0.002484952,0.0006397969],"domain_scores_gemma":[0.9974617,0.0006501814,0.0003951959,0.0003933818,0.0008773765,0.0002221219],"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":[0.00004193715,0.0001551361,0.0001877402,0.000008887703,0.000026903,0.000175995,0.002229844,0.912586,0.005488501,0.01108979,0.0005739874,0.06743524],"study_design_scores_gemma":[0.0000574792,0.001561561,0.00009875592,0.00002308321,0.00000422585,0.0001479987,0.003959247,0.9544805,0.007545207,0.00213067,0.02982908,0.0001622041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007539055,0.0001968945,0.9890347,0.001698071,0.0008725876,0.0001564394,3.245149e-7,0.00003420239,0.0004676869],"genre_scores_gemma":[0.9467866,0.0001071993,0.05139849,0.00006796445,0.0002287232,0.00001100774,5.640703e-7,0.00001834361,0.001381052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9392476,"threshold_uncertainty_score":0.9997883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2234694362051712,"score_gpt":0.4278249643476039,"score_spread":0.2043555281424326,"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."}}