{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005377788,0.0003017011,0.0006772297,0.001403322,0.00009251407,0.000182028,0.001965326,0.0003059907,0.00008617321],"category_scores_gemma":[0.0001018625,0.000394245,0.0003018027,0.00293532,0.00007422347,0.0005768092,0.001922438,0.001012168,0.000007071609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003472419,"about_ca_system_score_gemma":0.0002389348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005733774,"about_ca_topic_score_gemma":0.00009599322,"domain_scores_codex":[0.99755,0.0002995363,0.0004826298,0.00105037,0.0002176786,0.000399786],"domain_scores_gemma":[0.9972567,0.0001329315,0.0006104424,0.001632076,0.0002313789,0.0001364761],"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":[0.000006868564,0.00003806292,0.04177734,0.00005603225,0.0004461574,0.0001259138,0.001097839,0.941169,0.00009528524,0.01508557,0.000001254213,0.0001006252],"study_design_scores_gemma":[0.0002318761,0.00008518474,0.00996433,0.0001344097,0.0003211609,4.297156e-7,0.0004847059,0.988154,0.0001050909,0.0001333225,0.00002786256,0.0003576356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3022441,0.00001893473,0.6963251,0.00001083495,0.0001448846,0.0001158001,4.172563e-7,0.00008802232,0.00105189],"genre_scores_gemma":[0.9951019,0.000137364,0.004011222,0.00004254106,0.00001584572,6.561197e-7,0.00007222542,0.0000141381,0.0006041603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6928577,"threshold_uncertainty_score":0.9998509,"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."}}