{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002919563,0.0009490285,0.0009582179,0.0002546306,0.000319165,0.0009564483,0.001415029,0.001023305,0.003464717],"category_scores_gemma":[0.01054412,0.0002673831,0.0005188591,0.0003234828,0.0007984659,0.002310806,0.001241514,0.002360714,0.0006286447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004598914,"about_ca_system_score_gemma":0.001144659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002797814,"about_ca_topic_score_gemma":0.002064684,"domain_scores_codex":[0.9992483,0.0002766844,0.00004821773,0.0001747936,0.0001743895,0.00007757248],"domain_scores_gemma":[0.993508,0.003628913,0.000335045,0.001299368,0.0009109296,0.0003178209],"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":[0.001081299,0.0009150148,0.003680596,0.0002559754,0.0001484934,0.0001382243,0.0002463723,0.6785262,0.0179341,0.01300233,0.003835422,0.280236],"study_design_scores_gemma":[0.00004542799,0.0002175996,0.0004825705,0.00001695093,0.00001605357,0.00002759652,0.00001535811,0.9905521,0.003263148,0.004064896,0.001285733,0.00001256717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1990598,0.001560948,0.7907121,0.0009680566,0.0003964925,0.0001534285,0.0001614353,0.001724239,0.005263492],"genre_scores_gemma":[0.8537812,0.0003909299,0.1426562,0.000342231,0.0001163615,0.0001107533,0.0002433077,0.0001514537,0.002207679],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003464717,"threshold_uncertainty_score":0.01544034,"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."}}