{"id":"W3171711942","doi":"10.1109/syscon48628.2021.9447080","title":"Optimization of Deep Reinforcement Learning with Hybrid Multi-Task Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Machine learning; Deep learning; Learning classifier system; Robot learning; Multi-task learning; Active learning (machine learning); Engineering; Robot","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":[],"consensus_categories":[],"category_scores_codex":[0.0002726468,0.0001772033,0.0002241235,0.0001136777,0.0001895408,0.0001514587,0.0004148084,0.00004235627,0.0002070989],"category_scores_gemma":[0.0002307743,0.0001587944,0.00006060869,0.000488071,0.00004579938,0.0005070736,0.0003362988,0.0003278322,0.00003095631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005709774,"about_ca_system_score_gemma":0.0001096353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001512864,"about_ca_topic_score_gemma":0.000002503468,"domain_scores_codex":[0.9982653,0.0001254363,0.0003943989,0.000376849,0.0005111091,0.000326852],"domain_scores_gemma":[0.9987063,0.0001032967,0.0002906226,0.000432835,0.0003787439,0.00008823395],"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":[0.000005465552,0.00001915545,0.002133731,0.00002551396,0.0000376192,0.00002435801,0.0004242641,0.9929916,0.000347587,0.002159229,0.00001171129,0.001819816],"study_design_scores_gemma":[0.000647247,0.0002502481,0.0001468185,0.00004168994,0.00001291251,0.00003081121,0.0001981589,0.9900589,0.007597586,0.000003116987,0.0008055586,0.0002069815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005907516,0.0000448829,0.9895357,0.0001017966,0.0000938935,0.0001206086,2.883232e-8,0.0002339315,0.009278357],"genre_scores_gemma":[0.61998,0.00003559792,0.3731036,0.00007859772,0.00001411929,0.000005580424,0.0000195359,0.00001559528,0.006747434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6193892,"threshold_uncertainty_score":0.6475449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01323072726757158,"score_gpt":0.2300208503905229,"score_spread":0.2167901231229513,"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."}}