{"id":"W3208016380","doi":"10.3389/frai.2022.805823","title":"Investigation of independent reinforcement learning algorithms in multi-agent environments","year":2022,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Reinforcement learning; Algorithm; Artificial intelligence; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.001134232,0.0001781682,0.0002542113,0.0005654987,0.0001534464,0.00004784209,0.001022179,0.00005920949,0.00005667007],"category_scores_gemma":[0.0001029823,0.0002175664,0.00006006048,0.0008676409,0.0001087711,0.0003284661,0.0007349355,0.000635171,0.00001833025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006150085,"about_ca_system_score_gemma":0.0000808294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001796524,"about_ca_topic_score_gemma":0.00001371246,"domain_scores_codex":[0.9971186,0.000300495,0.0009219071,0.0004616372,0.0007933807,0.0004039627],"domain_scores_gemma":[0.9990979,0.00005290069,0.0003495376,0.000404354,0.00001935829,0.0000759211],"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":[0.0000141744,0.00004279019,0.02892777,0.000009215537,0.000008963679,0.00001705934,0.003919426,0.9461671,0.0007783294,0.002121595,0.00003602739,0.01795758],"study_design_scores_gemma":[0.00009784869,0.0001866199,0.002689176,0.00002326957,0.000002846007,0.000001484838,0.001653316,0.9783112,0.01479664,0.001567679,0.0004641453,0.0002057693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01521994,0.00008707384,0.9826191,0.0001065432,0.001427626,0.0003880935,5.245372e-7,0.00003181724,0.0001192473],"genre_scores_gemma":[0.9234158,0.00005086304,0.07595057,0.00007871775,0.00001322387,0.0000800772,0.00001004904,0.00001312163,0.0003875195],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9081959,"threshold_uncertainty_score":0.8872099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05814036785717878,"score_gpt":0.2710809898253303,"score_spread":0.2129406219681515,"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."}}