{"id":"W3134456772","doi":"10.48550/arxiv.2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","year":2021,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Lifelong learning; Computer science; Reinforcement learning; Testbed; Benchmark (surveying); Task (project management); Artificial intelligence; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001670608,0.0007780836,0.0009817872,0.0007173396,0.0005863003,0.002391102,0.00243936,0.001000492,0.00002054716],"category_scores_gemma":[0.002986751,0.0009099194,0.0005251477,0.0006561812,0.0001020868,0.0005922665,0.002762968,0.002119456,0.00002081104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205132,"about_ca_system_score_gemma":0.001492811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006452071,"about_ca_topic_score_gemma":0.0004852632,"domain_scores_codex":[0.9949713,0.0004086651,0.001081444,0.001448875,0.0008723103,0.001217425],"domain_scores_gemma":[0.9948729,0.0005883575,0.001137874,0.002121173,0.0008632784,0.0004164685],"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":[0.00004156885,0.0001174533,0.00441554,0.0003471465,0.000180313,0.0001571045,0.001126248,0.9224471,0.0008029299,0.05302052,0.00278453,0.01455956],"study_design_scores_gemma":[0.0005996166,0.0003034988,0.002457914,0.0004909789,0.00009260793,0.0001215013,0.0001351218,0.9861977,0.001380964,0.002640794,0.004627812,0.0009515192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006323928,0.0008966964,0.9813519,0.005351952,0.0009167761,0.002103689,0.00001309482,0.002049634,0.0009922914],"genre_scores_gemma":[0.5907589,0.0002145937,0.3980081,0.001735547,0.0003629989,0.001498061,0.0004173629,0.0001472878,0.006857144],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5844349,"threshold_uncertainty_score":0.9993352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01464353487020289,"score_gpt":0.2543663899315203,"score_spread":0.2397228550613174,"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."}}