{"id":"W7124240193","doi":"10.65109/jsvi2318","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Aggregate (composite); Reinforcement; Transformer","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":[0.003312903,0.001250659,0.00147439,0.0005288462,0.0006697263,0.001244487,0.002470305,0.001498722,0.002693845],"category_scores_gemma":[0.007264679,0.0006156171,0.0006451981,0.0005327853,0.001450893,0.002411439,0.002995519,0.002076835,0.0005309659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001081891,"about_ca_system_score_gemma":0.001778239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004518786,"about_ca_topic_score_gemma":0.005181109,"domain_scores_codex":[0.9987632,0.0005041985,0.00005693842,0.0003203292,0.0002057192,0.0001495953],"domain_scores_gemma":[0.9978154,0.001053086,0.00019477,0.0004715854,0.0002863316,0.0001788869],"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":[0.0002382958,0.0002118082,0.001934309,0.0001126177,0.0001384724,0.0001560795,0.0002312712,0.8239722,0.003346749,0.01578602,0.003230971,0.1506412],"study_design_scores_gemma":[0.00001654399,0.00003750376,0.00007263702,0.000007026307,0.00001030096,0.00001640471,0.00001168096,0.9918975,0.0007317172,0.006716437,0.0004769375,0.000005296941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01500892,0.0002037176,0.9813426,0.0002174562,0.00005971736,0.00006345929,0.0000353322,0.001696961,0.001371923],"genre_scores_gemma":[0.8012729,0.0001131781,0.1952908,0.0004050191,0.00006788482,0.0002041362,0.0001451536,0.0002072617,0.002293573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004518786,"threshold_uncertainty_score":0.01752049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02335311171161477,"score_gpt":0.2575649258979304,"score_spread":0.2342118141863156,"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."}}