{"id":"W3034724428","doi":"10.48550/arxiv.2003.00203","title":"Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts","year":2020,"lang":"en","type":"preprint","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":"Reinforcement learning; Computer science; Reuse; Transfer of learning; Artificial intelligence; Robustness (evolution); Task (project management); Context (archaeology); Machine learning; Policy learning; Dynamics (music); 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":[0.0002895622,0.0004822157,0.000644569,0.0006576093,0.0001257379,0.00009566186,0.002249999,0.0003918503,0.00004547639],"category_scores_gemma":[0.0001341973,0.0005717609,0.0002796871,0.001082126,0.0001672187,0.0003635395,0.001690767,0.001156598,0.00004165679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004545813,"about_ca_system_score_gemma":0.0003755034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004976864,"about_ca_topic_score_gemma":0.00004554236,"domain_scores_codex":[0.9971969,0.0002825388,0.0005661861,0.001089183,0.000268566,0.0005966342],"domain_scores_gemma":[0.9981632,0.0001772258,0.0002823826,0.0009919584,0.0001358209,0.0002493813],"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":[0.00005432448,0.00003269055,0.001031479,0.0001044674,0.00009331005,0.0002440495,0.002449016,0.9081187,0.0003274494,0.08713876,0.00002841474,0.000377356],"study_design_scores_gemma":[0.001144797,0.0002697685,0.0002859581,0.0001469938,0.00003566492,0.000003992314,0.0001385069,0.9941552,0.0006039543,0.001922722,0.000733573,0.0005588658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02286991,0.00004565073,0.9708722,0.000244797,0.000294003,0.0004817903,0.00000121858,0.0002067156,0.004983768],"genre_scores_gemma":[0.9970974,0.0001852206,0.001411135,0.0002538487,0.00009168592,0.000001989607,0.00002585085,0.00003235174,0.0009005368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9742275,"threshold_uncertainty_score":0.9996734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05375636255390823,"score_gpt":0.2086563624918888,"score_spread":0.1548999999379806,"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."}}