{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006198273,0.0007438136,0.0007666172,0.001963526,0.0008339138,0.003503547,0.003559808,0.0005986782,0.0001769561],"category_scores_gemma":[0.0007981302,0.0007262836,0.0004585097,0.001472721,0.000292629,0.0004312462,0.02282475,0.011447,0.0008204652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001988641,"about_ca_system_score_gemma":0.002028457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005001543,"about_ca_topic_score_gemma":0.00001011626,"domain_scores_codex":[0.9876817,0.001087687,0.001230943,0.002016885,0.005725592,0.002257187],"domain_scores_gemma":[0.9954544,0.0007084313,0.0003579416,0.001939479,0.0008601907,0.0006795331],"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":[0.00002050428,0.0000411063,0.0012807,0.001392507,0.0001585186,0.0004321329,0.003048803,0.9817831,0.0002081834,0.005975078,0.0009001109,0.00475928],"study_design_scores_gemma":[0.0003844796,0.0003758324,0.0002049267,0.002710905,0.00002013951,0.00003591127,0.0002594122,0.9802656,0.0005796783,0.008068682,0.006327871,0.0007665865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02877787,0.0007151171,0.9531518,0.0008981748,0.00379603,0.002124368,0.000008380561,0.001049426,0.0094789],"genre_scores_gemma":[0.9647744,0.0003147747,0.0175702,0.00004332284,0.0007212139,0.00009411985,0.0001015831,0.0001530496,0.01622734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9359965,"threshold_uncertainty_score":0.9999575,"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."}}