{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002506754,0.001593965,0.00139137,0.0007311124,0.0005947072,0.001039225,0.002692449,0.001384431,0.003388706],"category_scores_gemma":[0.006547979,0.0008961696,0.0007560203,0.000596212,0.001584533,0.001862022,0.002636087,0.001918733,0.0007274887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001683575,"about_ca_system_score_gemma":0.002074846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007404251,"about_ca_topic_score_gemma":0.005901418,"domain_scores_codex":[0.9989243,0.0003563012,0.00006365026,0.0002723291,0.0002046799,0.0001785865],"domain_scores_gemma":[0.9966605,0.001852857,0.0002609772,0.0006851308,0.0002702659,0.0002702752],"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":[0.0002705615,0.0001857043,0.0009400474,0.00005931155,0.0000592779,0.00006421033,0.00007957809,0.9271365,0.002397202,0.004930735,0.001559968,0.06231685],"study_design_scores_gemma":[0.00002536652,0.00004637342,0.00007567232,0.000003143307,0.000006527136,0.000007109377,0.000005203797,0.9939383,0.0004036569,0.005373601,0.0001107615,0.000004264587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1318757,0.0004289657,0.8569911,0.0006746946,0.00008987682,0.0002834468,0.0002071225,0.004342103,0.005107057],"genre_scores_gemma":[0.9038097,0.00009251801,0.09311488,0.0002183285,0.0000360076,0.000291469,0.000252945,0.0001593408,0.002024909],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007404251,"threshold_uncertainty_score":0.01472229,"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."}}