{"id":"W3035417664","doi":"10.48550/arxiv.2006.07262","title":"A Brief Look at Generalization in Visual Meta-Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Overfitting; Generalization; Computer science; Artificial intelligence; Meta learning (computer science); Scalability; Machine learning; Realization (probability); Artificial neural network; Task (project management); Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0003331037,0.0004606237,0.0006024088,0.0003834439,0.0001882754,0.0001978156,0.001565722,0.0002934435,0.0001712517],"category_scores_gemma":[0.00009552165,0.0005375319,0.0003489493,0.0008676859,0.00007325014,0.0004680164,0.004707737,0.000891294,0.0002123167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007080464,"about_ca_system_score_gemma":0.0002078081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000174331,"about_ca_topic_score_gemma":0.0000363516,"domain_scores_codex":[0.9972419,0.0002936132,0.000439008,0.001274062,0.0002575452,0.0004938566],"domain_scores_gemma":[0.9982871,0.00008972201,0.0005111401,0.0007790289,0.0001278837,0.0002050557],"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":[0.00001960725,0.0000197453,0.003166078,0.0000708752,0.0003278719,0.000213843,0.0004662916,0.9574779,0.0000538093,0.03802646,0.0001193452,0.00003812385],"study_design_scores_gemma":[0.0005590867,0.0001144081,0.0003477796,0.00004020696,0.0002632499,0.000002356649,0.00001945801,0.9940804,0.000193046,0.0007019557,0.003165603,0.0005124724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01911317,0.00005337923,0.9762028,0.0001721248,0.0003250837,0.0004230883,7.656787e-7,0.0003323071,0.003377214],"genre_scores_gemma":[0.9897994,0.0001789131,0.001662225,0.0003288756,0.00006231951,0.00000325524,0.00007949876,0.00003143776,0.007854058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745407,"threshold_uncertainty_score":0.9997076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025356039800561,"score_gpt":0.2165601146297081,"score_spread":0.114024510649652,"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."}}