{"id":"W4287647350","doi":"10.48550/arxiv.2010.01062","title":"Exploration in Approximate Hyper-State Space for Meta Reinforcement\\n Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; European Commission; Nvidia; Compute Canada; Microsoft Research","keywords":"Reinforcement learning; Task (project management); Meta learning (computer science); Computer science; State space; Artificial intelligence; Space (punctuation); Machine learning; State (computer science); Mathematics; Engineering; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004896877,0.0004365538,0.0005922994,0.0003704771,0.0001740235,0.0002721484,0.001639546,0.0002104674,0.0000189476],"category_scores_gemma":[0.0001697676,0.0005109712,0.0003324202,0.0007298653,0.00005980574,0.001029591,0.002009779,0.0008868789,0.00006420328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002657011,"about_ca_system_score_gemma":0.0001749638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007724124,"about_ca_topic_score_gemma":0.00001376802,"domain_scores_codex":[0.9975158,0.0001826658,0.0003988603,0.001211906,0.0001721547,0.0005186408],"domain_scores_gemma":[0.9980658,0.0001746455,0.0005452799,0.0008906749,0.0001637911,0.000159759],"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":[0.00003836512,0.00001438992,0.0002458988,0.0001659176,0.0002139325,0.00004497884,0.000760323,0.9446375,0.00003259211,0.05360158,0.0001167033,0.0001277827],"study_design_scores_gemma":[0.0006698093,0.0001338595,0.00002518629,0.00005390262,0.0001947273,8.008149e-7,0.00009896048,0.9841604,0.0002285212,0.01136412,0.00257907,0.0004906536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002439803,0.00003386961,0.993486,0.0005261427,0.0003518577,0.0009333069,0.000002344492,0.0003796493,0.001846961],"genre_scores_gemma":[0.9795994,0.0002411103,0.0138021,0.0001253112,0.00004771273,0.00002290533,0.00007177138,0.0000402463,0.0060494],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9796839,"threshold_uncertainty_score":0.9997342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1715914291665377,"score_gpt":0.2178853611837374,"score_spread":0.0462939320171997,"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."}}