{"id":"W4401157207","doi":"10.21203/rs.3.rs-4678044/v1","title":"Speeding up hierarchical reinforcement learning using state-independent temporal skills","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; State (computer science); Artificial intelligence; Psychology; Social psychology; 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":[0.0008454053,0.0006252317,0.0007101876,0.0003036055,0.0003104317,0.0005243474,0.001098439,0.0007786556,0.004435192],"category_scores_gemma":[0.004282263,0.0004097004,0.0003410917,0.0002507468,0.000658693,0.001250215,0.001355459,0.001618193,0.0005461622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000596894,"about_ca_system_score_gemma":0.001228492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004968215,"about_ca_topic_score_gemma":0.006643602,"domain_scores_codex":[0.9996518,0.0000634547,0.00001997788,0.00009787864,0.00009562432,0.00007124599],"domain_scores_gemma":[0.9983012,0.001062347,0.0001218478,0.0002116832,0.0001641914,0.0001386876],"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":[0.0005462045,0.0005452037,0.001772347,0.0001777125,0.00007654252,0.0001151132,0.0001388832,0.6830087,0.02069718,0.01609353,0.002603087,0.2742255],"study_design_scores_gemma":[0.00002677531,0.00004147492,0.0001089509,0.000003063039,0.000005300341,0.000006835728,0.000003866185,0.9950448,0.001194799,0.003435862,0.0001254928,0.000002705578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1396253,0.0001843159,0.85353,0.0002394809,0.00009259555,0.0001103674,0.00006426464,0.001611757,0.004541955],"genre_scores_gemma":[0.9281188,0.00004468511,0.0697998,0.00006729334,0.00001717358,0.00007896034,0.00005308594,0.00005239327,0.001767786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004968215,"threshold_uncertainty_score":0.01483715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07600609675111851,"score_gpt":0.397787467474971,"score_spread":0.3217813707238524,"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."}}