{"id":"W3136181012","doi":"10.1109/access.2021.3065710","title":"A Hybrid Multi-Task Learning Approach for Optimizing Deep Reinforcement Learning Agents","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Machine learning; Field (mathematics); Multi-task learning; Deep learning; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00125588,0.001034892,0.0009894916,0.0004058426,0.000362414,0.0007985412,0.001394824,0.001181905,0.001797188],"category_scores_gemma":[0.001859339,0.0004254026,0.0005598499,0.0003197964,0.0007106818,0.0007285876,0.001155261,0.001089805,0.0002750637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007958209,"about_ca_system_score_gemma":0.001143084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004832186,"about_ca_topic_score_gemma":0.003844978,"domain_scores_codex":[0.9995603,0.0001505938,0.00002245392,0.00008847626,0.0001023052,0.00007583931],"domain_scores_gemma":[0.9992995,0.0003180131,0.00009328041,0.00004148137,0.0001845706,0.00006315799],"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":[0.00003102422,0.00002644784,0.000218652,0.00002183535,0.00002156477,0.00003413781,0.00002101882,0.9854939,0.000697654,0.002199605,0.0002300634,0.01100396],"study_design_scores_gemma":[0.000004025047,0.00001517262,0.00001710132,0.000001339886,0.00000219723,0.000002965235,0.000001538135,0.9992961,0.00008975707,0.0004866607,0.00008166795,0.000001428059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02635513,0.000302191,0.9695503,0.0002400822,0.0000453004,0.00005858374,0.00002764559,0.0002620965,0.003158801],"genre_scores_gemma":[0.8955366,0.0001310173,0.1006238,0.0001906144,0.00004076266,0.0001888647,0.00005429434,0.00004402546,0.003189988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004832186,"threshold_uncertainty_score":0.00960809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0610404448592446,"score_gpt":0.314948900322499,"score_spread":0.2539084554632544,"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."}}