{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007300967,0.0002635828,0.000361913,0.0003372463,0.0001415342,0.0001139336,0.001362938,0.0001755031,0.000004528231],"category_scores_gemma":[0.00003278518,0.0002651938,0.0001014573,0.0003181922,0.0001949753,0.0005368716,0.0005453442,0.0004327367,0.000007312261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002223604,"about_ca_system_score_gemma":0.0007560699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003293891,"about_ca_topic_score_gemma":0.00002860676,"domain_scores_codex":[0.9975792,0.000016327,0.0005700577,0.0008274946,0.0006111722,0.0003957653],"domain_scores_gemma":[0.998531,0.0002407052,0.0003513925,0.0005513387,0.0002553646,0.00007012884],"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":[0.000005376171,0.00002253914,0.00004252757,0.00004211032,0.000002383088,0.000001541008,0.0003185546,0.9021589,0.001447497,0.02907916,0.000002443658,0.06687704],"study_design_scores_gemma":[0.000291447,0.0001670691,0.00006506494,0.0003489094,0.000003699316,0.000005115423,2.536999e-7,0.9193213,0.001453661,0.07802428,0.00006712568,0.0002520514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008775538,0.000129771,0.99743,0.0001850936,0.0002953346,0.0006611607,0.00000318054,0.00004040785,0.0003774946],"genre_scores_gemma":[0.4539626,0.00001704455,0.5447531,0.0002065963,0.0001365225,0.00004648618,0.00001655043,0.00001812811,0.0008429954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4530851,"threshold_uncertainty_score":0.99998,"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."}}