{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00141514,0.001060676,0.001201562,0.000562737,0.0004264041,0.0007337438,0.001270825,0.001235097,0.00326269],"category_scores_gemma":[0.00763326,0.0005954904,0.0004808586,0.000422578,0.001022227,0.002019486,0.00117538,0.002177006,0.001050796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007595898,"about_ca_system_score_gemma":0.001357297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00426728,"about_ca_topic_score_gemma":0.004803377,"domain_scores_codex":[0.9995734,0.0001154475,0.00002828429,0.0001324866,0.0000952258,0.00005520694],"domain_scores_gemma":[0.9983884,0.0009189163,0.0001241761,0.0002721183,0.0002061091,0.00009026923],"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":[0.0001995737,0.0002084517,0.001824967,0.0001629105,0.00006967639,0.0001156623,0.0001912653,0.7000263,0.005190128,0.01946191,0.004867258,0.267682],"study_design_scores_gemma":[0.00001149973,0.0000315539,0.00007592146,0.00001025692,0.000003945602,0.00002081236,0.000006147496,0.9918057,0.0009740773,0.006417664,0.0006370399,0.000005456767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01747357,0.0006102809,0.978269,0.0001712454,0.00007231851,0.00005111632,0.00003946691,0.002007289,0.001305725],"genre_scores_gemma":[0.6771604,0.0004186872,0.3175942,0.0003861797,0.00008847161,0.0002011492,0.000308175,0.0004588623,0.003383826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00426728,"threshold_uncertainty_score":0.0109148,"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."}}