{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000482457,0.0001580715,0.0002293862,0.00005419665,0.00009210123,0.00006429689,0.00090558,0.00006419059,0.00002447252],"category_scores_gemma":[0.0005540651,0.0001629036,0.00006416405,0.0006179765,0.00003133098,0.0002205878,0.0003082385,0.0004390373,0.00008331942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008095564,"about_ca_system_score_gemma":0.0001952016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002430933,"about_ca_topic_score_gemma":0.00002018808,"domain_scores_codex":[0.9982764,0.0001551912,0.0003854067,0.0003092022,0.000399631,0.0004741741],"domain_scores_gemma":[0.9989797,0.0001308938,0.000248243,0.0003570538,0.00016011,0.0001239671],"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":[0.000009056734,0.00001114199,0.002487641,0.00001866621,0.00003323444,0.000002102329,0.0008525922,0.9882504,0.000827658,0.00241575,0.0001024381,0.004989312],"study_design_scores_gemma":[0.0004212394,0.0005545322,0.002223168,0.000006802191,0.000005804539,0.000001268184,0.00001042688,0.9864545,0.001867406,0.000008144958,0.008278321,0.0001683924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001439241,0.001287803,0.9960057,0.0002646534,0.00007300463,0.0001534681,1.501246e-7,0.0001595842,0.0006163568],"genre_scores_gemma":[0.9895111,0.0002485661,0.009437524,0.000379784,0.00002136213,0.000005022069,0.0000166517,0.00001739952,0.000362598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9880719,"threshold_uncertainty_score":0.6643016,"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."}}