{"id":"W3185541071","doi":"","title":"Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Machine learning; Artificial intelligence; Transfer of learning; Reuse; Context (archaeology); Task (project management); Bayesian probability; Engineering","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":[0.0007407441,0.0003070765,0.0004627408,0.0005450668,0.0001142398,0.0001313286,0.0009605965,0.0001790882,0.0001491256],"category_scores_gemma":[0.0008757324,0.00032296,0.0001309926,0.001898916,0.0001947813,0.0003611309,0.0002617973,0.0005549738,0.00005069255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003605805,"about_ca_system_score_gemma":0.0003781205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001114903,"about_ca_topic_score_gemma":0.001289969,"domain_scores_codex":[0.9963885,0.0003235947,0.001273806,0.0006292852,0.0006361855,0.0007486546],"domain_scores_gemma":[0.9983697,0.0004778997,0.0001397803,0.000650998,0.0002267464,0.0001348975],"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":[0.00003871293,0.00008595525,0.000323595,0.00002252266,0.00001333259,0.00009800476,0.006812552,0.8333458,0.006573731,0.1167647,0.000006336461,0.03591469],"study_design_scores_gemma":[0.0001554912,0.0002284047,0.0000757289,0.0001322209,0.000004143466,0.00001514394,0.001016291,0.9247836,0.06667003,0.005776791,0.0007781904,0.0003639817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0178021,0.0001435226,0.9778465,0.0007409882,0.0003448264,0.0003008406,5.034385e-7,0.0000747107,0.002746017],"genre_scores_gemma":[0.9953175,0.00009237086,0.00375067,0.00040664,0.00008703486,0.00002862503,0.00001303542,0.00001865457,0.0002854966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9775154,"threshold_uncertainty_score":0.9999223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03181191723208893,"score_gpt":0.2972237819968313,"score_spread":0.2654118647647424,"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."}}