{"id":"W3108183475","doi":"","title":"Skill Transfer via Partially Amortized Hierarchical Planning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Suite; Reinforcement learning; Leverage (statistics); Task (project management); Adaptation (eye); Knowledge transfer; Amortization; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002320851,0.0004436765,0.0005157822,0.0002154544,0.0001917899,0.000222511,0.002734007,0.0003750361,0.00005847904],"category_scores_gemma":[0.00006234707,0.0005209679,0.0003415747,0.0005653143,0.0001495951,0.0003539903,0.001934851,0.001503999,0.0002113857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001511588,"about_ca_system_score_gemma":0.0002723711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002634817,"about_ca_topic_score_gemma":0.000003820026,"domain_scores_codex":[0.9972267,0.0002329522,0.0003756027,0.001361509,0.0002311596,0.0005721352],"domain_scores_gemma":[0.9979867,0.0001645379,0.0001555753,0.00120421,0.0001046124,0.0003844042],"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":[0.0000475529,0.00002903944,0.001329384,0.00006029407,0.0001196019,0.0008266066,0.0007895793,0.9558272,0.00008341215,0.04051698,0.0001448518,0.0002254462],"study_design_scores_gemma":[0.0006794745,0.0001080786,0.001374669,0.00009513821,0.00007914156,0.000005552916,0.00001882596,0.9872864,0.0001596789,0.008519003,0.001097565,0.000576504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03056204,0.00002269048,0.9645582,0.0004124644,0.0006832249,0.0003384329,0.000003627302,0.0006330679,0.002786255],"genre_scores_gemma":[0.99272,0.00003727619,0.005789894,0.000403959,0.0001393664,0.00000127326,0.00002719814,0.00003339385,0.0008476159],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.962158,"threshold_uncertainty_score":0.9997242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08606900475964419,"score_gpt":0.2063541069875937,"score_spread":0.1202851022279496,"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."}}