{"id":"W3136163870","doi":"10.48550/arxiv.2011.13897","title":"Latent Skill Planning for Exploration and Transfer","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Leverage (statistics); Suite; Task (project management); Adaptation (eye); Amortization; Knowledge transfer; Transfer of learning; Artificial intelligence; Machine learning; Human–computer interaction; Knowledge management","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":[],"consensus_categories":[],"category_scores_codex":[0.00005863132,0.00007774146,0.00008010323,0.00003869514,0.00009958383,0.00005473074,0.0002535217,0.00003582399,0.00000364159],"category_scores_gemma":[0.00001900183,0.00008673711,0.0000342373,0.0002074282,0.00002251829,0.000646011,0.00006765663,0.00006624301,0.00001308487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001733302,"about_ca_system_score_gemma":0.00001532151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001880751,"about_ca_topic_score_gemma":3.412678e-7,"domain_scores_codex":[0.9994512,0.00001926973,0.00007317731,0.0002809999,0.00003647646,0.0001388928],"domain_scores_gemma":[0.9996635,0.00005202938,0.00002302838,0.0001314823,0.00003738905,0.00009262328],"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":[0.00001432675,0.000004142135,0.001015442,0.00001342629,0.00001055328,0.00001436168,0.001303303,0.9110575,0.00009248418,0.08618052,0.00008239188,0.0002115316],"study_design_scores_gemma":[0.0004674717,0.0001426528,0.0003065958,0.000008715294,0.00001122632,6.418433e-7,0.00009812376,0.9966184,0.0002706959,0.0009471669,0.001017885,0.0001104606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0383627,0.000009131836,0.9604654,0.0005671534,0.00005896452,0.0001391146,6.167821e-7,0.0001095083,0.0002873561],"genre_scores_gemma":[0.9966606,0.00001898035,0.002722812,0.0003221517,0.00002521534,3.857245e-7,0.000002800428,0.000005513583,0.0002415337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9582979,"threshold_uncertainty_score":0.3537037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1479268894563486,"score_gpt":0.193037985472503,"score_spread":0.04511109601615435,"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."}}