{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001402258,0.0009447442,0.001238317,0.0005384186,0.0003724956,0.001048484,0.001462745,0.001322145,0.002917755],"category_scores_gemma":[0.006469371,0.000535076,0.0005807705,0.000458595,0.001648503,0.001924621,0.002001808,0.001922359,0.0004374295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001168576,"about_ca_system_score_gemma":0.001037955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002069753,"about_ca_topic_score_gemma":0.00252857,"domain_scores_codex":[0.9993968,0.0002991183,0.00003342914,0.0001150384,0.00008710418,0.00006845165],"domain_scores_gemma":[0.997542,0.001611135,0.0002290283,0.0002858145,0.0001725097,0.0001594125],"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":[0.00011489,0.00006128944,0.001015149,0.00006282335,0.00004672238,0.00005494726,0.00007489043,0.952856,0.0009389899,0.02034557,0.0008340739,0.02359457],"study_design_scores_gemma":[0.000009105443,0.0000230805,0.00004435999,0.000006434468,0.000003620268,0.000007137457,0.000005113515,0.9906549,0.0001542681,0.008911991,0.0001767569,0.00000322541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06130664,0.000567116,0.932872,0.0006306829,0.00005409851,0.00006814799,0.0000985619,0.0007857018,0.003617107],"genre_scores_gemma":[0.9107908,0.0002139763,0.08560833,0.000249874,0.00004248297,0.0002536993,0.0001458774,0.00009534322,0.002599684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002917755,"threshold_uncertainty_score":0.009760916,"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."}}