{"id":"W3042725540","doi":"10.48550/arxiv.2007.07011","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"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); Variety (cybernetics); Training (meteorology); Control (management); Artificial intelligence; Machine learning; Cognitive psychology; Economics; Political science; Engineering; Psychology; Management","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":[0.001428178,0.001080498,0.001208313,0.0005687203,0.000437354,0.0007556464,0.00130258,0.001299772,0.003256868],"category_scores_gemma":[0.008032189,0.0006180565,0.0004873779,0.0004334251,0.001080269,0.002110649,0.001232248,0.002219675,0.001061726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007616364,"about_ca_system_score_gemma":0.001340581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004018379,"about_ca_topic_score_gemma":0.004569552,"domain_scores_codex":[0.9995561,0.000123216,0.00002893604,0.000138523,0.00009752575,0.00005572924],"domain_scores_gemma":[0.9982998,0.0009686201,0.0001342881,0.0002930278,0.0002080849,0.00009620652],"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":[0.0001977176,0.0001986077,0.001822072,0.0001675185,0.00007180408,0.0001173069,0.0001912567,0.7214813,0.005364405,0.02147836,0.004903978,0.2440058],"study_design_scores_gemma":[0.00001109471,0.00002783076,0.00007168621,0.00000984061,0.000003686848,0.00001978796,0.000005763355,0.9913467,0.0009645495,0.00691007,0.0006236571,0.000005314537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01615509,0.00056543,0.9798995,0.0001712636,0.00006776414,0.00004722617,0.00003893594,0.001845989,0.001208804],"genre_scores_gemma":[0.6670573,0.0004189568,0.3275917,0.000388565,0.00009358247,0.0002056902,0.0003093393,0.0004874329,0.003447562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004018379,"threshold_uncertainty_score":0.01089525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1563627802819452,"score_gpt":0.2347216323033455,"score_spread":0.0783588520214003,"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."}}