{"id":"W2594903727","doi":"10.48550/arxiv.1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Observability; Artificial intelligence; Set (abstract data type); Artificial neural network; Simple (philosophy); Architecture; Memory map; Deep learning; Shared memory; Parallel computing; 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":[0.0003680587,0.0005139177,0.0004963663,0.0002881813,0.0007730228,0.0005569473,0.004080839,0.0004084467,0.00004526284],"category_scores_gemma":[0.0001860691,0.0006003455,0.0003969909,0.000144952,0.0001538703,0.0006326951,0.0036239,0.001105264,0.00006471768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003261442,"about_ca_system_score_gemma":0.0002074991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006482434,"about_ca_topic_score_gemma":0.00001446508,"domain_scores_codex":[0.9973392,0.0001215288,0.0003509417,0.001283667,0.0002112276,0.0006934559],"domain_scores_gemma":[0.9961488,0.0001594883,0.0009131315,0.002264465,0.0002856208,0.0002285045],"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":[0.00003418745,0.000007983516,0.00041209,0.0001559941,0.0001164248,0.00007914371,0.0002950688,0.9742131,0.00001663045,0.02345428,0.0002651718,0.0009499631],"study_design_scores_gemma":[0.0008354995,0.0001459916,0.000248698,0.00007610407,0.00008868625,0.000003629176,0.00005938763,0.9912788,0.0001054228,0.004224052,0.002306543,0.0006271667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005167604,0.00005117883,0.9881552,0.0001421021,0.002246397,0.0008075247,0.000001845033,0.0004055247,0.003022642],"genre_scores_gemma":[0.9761497,0.00005160927,0.005706426,0.00009852994,0.0002017503,0.000004225968,0.00006987502,0.00004039406,0.01767744],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9824488,"threshold_uncertainty_score":0.9996448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666945800872272,"score_gpt":0.2102999486985228,"score_spread":0.1436053686112956,"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."}}