{"id":"W2784831250","doi":"10.1109/icra.2018.8462977","title":"Cross-Domain Transfer in Reinforcement Learning Using Target Apprentice","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Transfer of learning; Task (project management); Domain (mathematical analysis); Sample (material); Artificial intelligence; Apprenticeship; Negative transfer; Sample complexity; Reuse; Multi-task learning; Machine learning; Policy learning; Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001466703,0.0005814732,0.0005852805,0.0004930049,0.000241056,0.001097719,0.002483793,0.0004854808,0.0005790382],"category_scores_gemma":[0.0001137983,0.0005990182,0.000197161,0.0004839747,0.0001741677,0.0006264886,0.002842754,0.001677977,0.0001635383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004202958,"about_ca_system_score_gemma":0.0003413975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002163096,"about_ca_topic_score_gemma":0.000006896411,"domain_scores_codex":[0.9955481,0.0002600338,0.001115849,0.001187537,0.000964492,0.0009239506],"domain_scores_gemma":[0.9978625,0.0001118992,0.0002420404,0.001399451,0.0002150354,0.0001691033],"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":[0.00001161831,0.00002206142,0.003940451,0.0001582216,0.00004490356,0.00002035001,0.001623694,0.9885763,0.0001756167,0.005262335,0.00004588467,0.0001185693],"study_design_scores_gemma":[0.0006006664,0.0001159753,0.0004724313,0.0002661484,0.00001207079,0.000007499069,0.00004611232,0.9929179,0.0009232761,0.0009025936,0.003047729,0.0006875999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03390442,0.00004812312,0.9440224,0.00007964824,0.001452049,0.000638532,5.252664e-7,0.000382811,0.01947154],"genre_scores_gemma":[0.7075678,0.00002668636,0.2860272,0.0002190973,0.0002395486,0.00003848763,0.00004036741,0.00006034655,0.005780471],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6736634,"threshold_uncertainty_score":0.9999393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03322628946258945,"score_gpt":0.2995726163778216,"score_spread":0.2663463269152322,"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."}}