{"id":"W2962985403","doi":"","title":"Universal Successor Representations for Transfer Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Initialization; Successor cardinal; Artificial intelligence; Set (abstract data type); Transfer of learning; Focus (optics); Function (biology); Machine learning; Reinforcement; Value (mathematics); Mathematics; Programming language","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":[0.001560365,0.0007799943,0.0009175434,0.0004774175,0.0002927654,0.0008244071,0.001130453,0.001103663,0.003681471],"category_scores_gemma":[0.006114143,0.0003301401,0.0005086372,0.0003823433,0.001198255,0.002162933,0.001392428,0.001996082,0.0005133658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009511464,"about_ca_system_score_gemma":0.0009395495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001319348,"about_ca_topic_score_gemma":0.001420355,"domain_scores_codex":[0.999507,0.0001919006,0.00002933837,0.000117438,0.00009533032,0.00005913292],"domain_scores_gemma":[0.9985262,0.0007918054,0.0001490245,0.0002620974,0.00017771,0.00009309008],"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":[0.0001343343,0.0001271734,0.0007344086,0.0001551947,0.00005581733,0.0001246471,0.0001996712,0.7598742,0.002682212,0.1130683,0.002188273,0.1206558],"study_design_scores_gemma":[0.0000121713,0.00004215223,0.00005505778,0.00001262729,0.000006018766,0.00001795083,0.00000837243,0.9507148,0.0004950035,0.04801873,0.0006098914,0.000007313164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02477635,0.0003484821,0.9707762,0.000271156,0.00005669814,0.00004875366,0.00006538667,0.00074205,0.002914975],"genre_scores_gemma":[0.8784943,0.0002974258,0.116649,0.0001969263,0.00003879576,0.0002539477,0.0001851645,0.0001083067,0.003776105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003681471,"threshold_uncertainty_score":0.01231581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05728557116336094,"score_gpt":0.3472003823606163,"score_spread":0.2899148111972554,"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."}}