{"id":"W3104090274","doi":"","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Forgetting; Lifelong learning; Computer science; Train; Task (project management); Reuse; Process (computing); Function (biology); Artificial intelligence; Variety (cybernetics); Control (management); Machine learning; Cognitive psychology; Economics; Engineering; Management; Political science; Psychology","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":[0.0001805016,0.0001522185,0.0002334158,0.0001925434,0.0002215625,0.00006501129,0.0005366154,0.00005574789,0.000006236892],"category_scores_gemma":[0.0002942629,0.0001695976,0.0001405402,0.0007412297,0.00006915972,0.0004825491,0.0001712268,0.000171465,0.000008937172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004965216,"about_ca_system_score_gemma":0.0001101099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000454425,"about_ca_topic_score_gemma":0.000004962499,"domain_scores_codex":[0.9988657,0.0000826519,0.0001973513,0.0004123174,0.00008411404,0.0003578551],"domain_scores_gemma":[0.9991223,0.0001622715,0.0002258847,0.0001874537,0.0001013805,0.000200698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001030648,0.0000465454,0.03853024,0.0001057987,0.0001174363,0.0000245415,0.05804554,0.2136999,0.004130241,0.6694537,0.00008492617,0.01565807],"study_design_scores_gemma":[0.001115385,0.0002385744,0.003795591,0.00003527063,0.00001886449,0.000002722172,0.005368716,0.9817103,0.0006710799,0.00147697,0.005277582,0.0002890065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2962976,0.000008003834,0.7013786,0.0006150801,0.00005075876,0.0001309555,0.000001752993,0.0001407536,0.001376488],"genre_scores_gemma":[0.9928966,0.000005930393,0.005906614,0.0005373904,0.00009864222,6.253919e-7,0.000003181431,0.00001553862,0.0005354511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7680103,"threshold_uncertainty_score":0.6915991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1349434077588783,"score_gpt":0.2164568420578213,"score_spread":0.08151343429894298,"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."}}