{"id":"W2996283994","doi":"10.48550/arxiv.2002.05822","title":"Frequency-based Search-control in Dyna","year":2020,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Bellman equation; Benchmark (surveying); Artificial intelligence; Function (biology); Machine learning; Mathematical optimization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001872999,0.0008148895,0.0009510352,0.0006492015,0.0005994793,0.001092589,0.001115862,0.000903269,0.002902696],"category_scores_gemma":[0.007565818,0.0004635305,0.0004616017,0.0003961074,0.001802059,0.001350909,0.001418745,0.001287987,0.0002998138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001317337,"about_ca_system_score_gemma":0.001421027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004240556,"about_ca_topic_score_gemma":0.00411582,"domain_scores_codex":[0.9991291,0.0003197532,0.00005977028,0.0002028152,0.0002021812,0.00008642815],"domain_scores_gemma":[0.996586,0.002303116,0.0003725015,0.000274934,0.0002955192,0.0001680986],"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":[0.0001609509,0.00008861767,0.001491192,0.0001446988,0.00005939554,0.00008306754,0.0001703758,0.8657593,0.004349256,0.08016598,0.0009504954,0.04657681],"study_design_scores_gemma":[0.000017831,0.00004585833,0.00009400128,0.000008200223,0.000007005607,0.00001654461,0.000008136783,0.9822218,0.0007647139,0.01634262,0.0004646463,0.000008673578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0418553,0.0002745759,0.9528864,0.0002882364,0.00004371944,0.00007187722,0.00004689257,0.0006947014,0.00383822],"genre_scores_gemma":[0.890536,0.000116664,0.106706,0.000140277,0.00002184355,0.0001876543,0.00004984797,0.00009612555,0.002145582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004240556,"threshold_uncertainty_score":0.009905517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01453165029516121,"score_gpt":0.2300616995247914,"score_spread":0.2155300492296302,"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."}}