{"id":"W3081310128","doi":"10.3390/electronics9091363","title":"A Survey of Multi-Task Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"Electronics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Forgetting; Deep learning; Transfer of learning; Task (project management); Active learning (machine learning); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001462719,0.001290274,0.001357449,0.0008440828,0.000294025,0.00145782,0.001702462,0.001297777,0.003347606],"category_scores_gemma":[0.00310717,0.0006225387,0.0007290186,0.001564962,0.0005669749,0.001753833,0.001176823,0.00155126,0.0009669823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125623,"about_ca_system_score_gemma":0.001258485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00313265,"about_ca_topic_score_gemma":0.002287172,"domain_scores_codex":[0.999347,0.0001656148,0.00007665298,0.0001512569,0.0002049662,0.00005450429],"domain_scores_gemma":[0.9989974,0.0005849884,0.00005927878,0.00009096216,0.000214616,0.00005276046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001269543,0.000174405,0.001569113,0.001311505,0.0001588777,0.00008886593,0.00008758921,0.1924558,0.001289473,0.03299874,0.007037034,0.7627016],"study_design_scores_gemma":[0.00003820771,0.0002977405,0.001066125,0.0005622506,0.00009063315,0.0002142858,0.00007100674,0.885215,0.002366213,0.04919489,0.06082463,0.00005907372],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.009830999,0.1674594,0.7975252,0.002021105,0.0005118909,0.0001368616,0.0001966879,0.0009007192,0.02141696],"genre_scores_gemma":[0.4763805,0.2443122,0.2540784,0.001716045,0.001611258,0.0005568177,0.0009250375,0.0003999414,0.02001974],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003347606,"threshold_uncertainty_score":0.01119888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0304471569031292,"score_gpt":0.2600883677161803,"score_spread":0.2296412108130511,"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."}}