{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001574918,0.001175245,0.0009842034,0.0005657303,0.0004972222,0.000976889,0.001961402,0.001079242,0.008144203],"category_scores_gemma":[0.007074319,0.000610391,0.0007736481,0.0005633842,0.00161788,0.002005581,0.002572942,0.002547573,0.001381283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001551892,"about_ca_system_score_gemma":0.002465283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003839219,"about_ca_topic_score_gemma":0.004514314,"domain_scores_codex":[0.9991974,0.0002673613,0.00004560636,0.0002249828,0.0001482376,0.0001162709],"domain_scores_gemma":[0.9978224,0.001186637,0.0001696683,0.0005152581,0.0001478254,0.0001582318],"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":[0.0002941419,0.0002817422,0.001452312,0.000264951,0.0000737482,0.0001029566,0.0001672151,0.7306595,0.004221733,0.05733128,0.004112576,0.2010379],"study_design_scores_gemma":[0.00003266105,0.00007233198,0.000136411,0.00001504193,0.000009884305,0.00001505447,0.00001187305,0.9403905,0.0008420088,0.05751517,0.0009509415,0.000008029907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0160308,0.0003126025,0.9776585,0.0003768265,0.00005119083,0.0001304949,0.0001447195,0.002012047,0.003282783],"genre_scores_gemma":[0.7179636,0.0003127499,0.2753499,0.0002603173,0.00007289498,0.0007661228,0.000456865,0.0003736808,0.004443886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008144203,"threshold_uncertainty_score":0.02724504,"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."}}