{"id":"W3126150352","doi":"10.48550/arxiv.2102.03718","title":"An Analysis of Frame-skipping in Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Frame (networking); Task (project management); Inertia; Offset (computer science); Consistency (knowledge bases); Action (physics); Artificial intelligence; Machine learning; Algorithm","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":[0.005292586,0.001426318,0.001416703,0.0007983628,0.0007457297,0.001129017,0.002313884,0.001644198,0.006024861],"category_scores_gemma":[0.02118119,0.0007041519,0.000948855,0.0006459443,0.002055481,0.002468983,0.001653198,0.003039285,0.0004284912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002618328,"about_ca_system_score_gemma":0.001785522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006957761,"about_ca_topic_score_gemma":0.003763414,"domain_scores_codex":[0.9980444,0.0007073873,0.00008330927,0.0003361903,0.000542674,0.0002861102],"domain_scores_gemma":[0.9888334,0.008574435,0.0008236003,0.000597483,0.0006695102,0.0005014988],"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":[0.0002682165,0.0001426429,0.001372931,0.0002228881,0.00006715381,0.0001852237,0.0001915351,0.7989452,0.002452098,0.1527848,0.001906985,0.04146039],"study_design_scores_gemma":[0.00001549429,0.00007002753,0.000174001,0.00001603629,0.00001167606,0.00001817921,0.000006068205,0.9741072,0.000262156,0.02489785,0.0004133394,0.000007931538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03942628,0.001270096,0.9484927,0.000716445,0.00008773275,0.000122638,0.00009195086,0.0003810396,0.009411172],"genre_scores_gemma":[0.8896659,0.001028774,0.1002017,0.0004406713,0.000203834,0.0004312395,0.0001879921,0.0002522579,0.00758767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006957761,"threshold_uncertainty_score":0.02799016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05482070555975511,"score_gpt":0.2092527155128376,"score_spread":0.1544320099530825,"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."}}