{"id":"W3015100386","doi":"10.48550/arxiv.2004.00600","title":"Work in Progress: Temporally Extended Auxiliary Tasks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Robustness (evolution); Reinforcement learning; Task (project management); Autoencoder; Trajectory; Sensitivity (control systems); Artificial intelligence; Machine learning; Algorithm; Deep learning; 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"],"consensus_categories":[],"category_scores_codex":[0.0003009029,0.0004221259,0.0004572604,0.0003539478,0.00009543377,0.0002322009,0.003337577,0.0003740445,0.00003003524],"category_scores_gemma":[0.00006954189,0.0005090873,0.0002046783,0.001410508,0.000163828,0.0004496889,0.004183506,0.001329797,0.0002278334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002936165,"about_ca_system_score_gemma":0.0004022449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004125675,"about_ca_topic_score_gemma":0.000007938605,"domain_scores_codex":[0.9972721,0.000214121,0.0003648114,0.001427774,0.0001999742,0.0005212089],"domain_scores_gemma":[0.9976617,0.00008738526,0.0003903702,0.001517922,0.0001076674,0.0002350293],"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":[0.00004706188,0.00006255502,0.02124872,0.00009670344,0.00005809907,0.001394458,0.0004119736,0.9401514,0.000002765758,0.03507608,0.0008159237,0.0006342591],"study_design_scores_gemma":[0.0006594707,0.0001013543,0.01580939,0.0003211129,0.00003392682,0.000002886572,0.00005856272,0.9700271,0.00001919261,0.0106266,0.001597489,0.0007429292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01830561,0.0001037403,0.9748517,0.000855274,0.000732915,0.0006243357,0.000002621289,0.0006048409,0.003918976],"genre_scores_gemma":[0.9843689,0.00007062784,0.01363129,0.0001990832,0.00007207219,0.00000239674,0.00002393695,0.00002883475,0.001602855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9660633,"threshold_uncertainty_score":0.9997361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08161985637333861,"score_gpt":0.2053707032589729,"score_spread":0.1237508468856343,"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."}}