{"id":"W2937081431","doi":"10.1007/978-3-030-16670-0_11","title":"A Model of External Memory for Navigation in Partially Observable Visual Reinforcement Learning Tasks","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Reinforcement learning; Observability; Recall; Auxiliary memory; State (computer science); Probabilistic logic; Artificial intelligence; Memory model; Process (computing); Human–computer interaction; Shared memory; Cognitive psychology; 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":[0.0006265927,0.0007319015,0.001609868,0.0005438869,0.0005155482,0.002255569,0.003503806,0.002438016,0.01070233],"category_scores_gemma":[0.003293041,0.0006451815,0.001024544,0.0009211304,0.001259052,0.002259815,0.00142231,0.00175156,0.0009829815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001510632,"about_ca_system_score_gemma":0.0013463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01190227,"about_ca_topic_score_gemma":0.007557062,"domain_scores_codex":[0.9996313,0.00009826309,0.0000220836,0.0001078365,0.00005401015,0.00008653801],"domain_scores_gemma":[0.9988686,0.0005758724,0.0001641452,0.0001072867,0.0001588449,0.0001250706],"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":[0.0001849741,0.0001135216,0.0005918663,0.0001201303,0.00008081368,0.000212939,0.0001468731,0.8217123,0.001771142,0.1564694,0.001688755,0.01690735],"study_design_scores_gemma":[0.00003303974,0.00003648784,0.0001286514,0.00000712057,0.0000139852,0.00002122279,0.00000949591,0.9586708,0.0001337525,0.04067661,0.0002584888,0.00001032666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1505575,0.0009371651,0.8181015,0.001799151,0.0002704255,0.00009235711,0.0009392065,0.001015554,0.02628716],"genre_scores_gemma":[0.9544094,0.0004207001,0.02598475,0.0001235105,0.00007509942,0.0001633812,0.0002638898,0.00008419291,0.01847508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01190227,"threshold_uncertainty_score":0.0358029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02948238713968614,"score_gpt":0.2753781425012197,"score_spread":0.2458957553615336,"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."}}