{"id":"W4389782639","doi":"10.1038/s41598-023-49847-y","title":"Temporal encoding in deep reinforcement learning agents","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; McGill University; McGill University Health Centre","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Nvidia","keywords":"Mnemonic; Reinforcement learning; Encoding (memory); Computer science; Task (project management); Carry (investment); Working memory; Recurrent neural network; Reinforcement; Representation (politics); Neuroscience; Artificial intelligence; Artificial neural network; Cognition; Cognitive psychology; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009553118,0.0004561219,0.0006257909,0.0002541593,0.0002385162,0.0007063416,0.0009957426,0.0007639013,0.002412996],"category_scores_gemma":[0.003583255,0.0002953387,0.0002799263,0.0002107687,0.0006354704,0.00128774,0.0008509569,0.001157419,0.0002647167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009290848,"about_ca_system_score_gemma":0.0007436175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003689416,"about_ca_topic_score_gemma":0.004942038,"domain_scores_codex":[0.9997234,0.00009178342,0.00001907254,0.00005209422,0.00005989282,0.00005373705],"domain_scores_gemma":[0.9990922,0.0004805562,0.0001137839,0.00007776381,0.0001675674,0.00006812878],"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":[0.0001082711,0.0000600376,0.0007415553,0.0000376995,0.00002934419,0.0000530846,0.00005209495,0.9332701,0.001439537,0.02769924,0.0008071176,0.03570186],"study_design_scores_gemma":[0.000004594675,0.000009771788,0.00001927398,0.000001715072,0.000001641231,0.000002999514,0.000001634691,0.9948092,0.0001479177,0.004901857,0.0000980411,0.000001419178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1009936,0.0004638119,0.8906291,0.0007435181,0.0001210131,0.00005628881,0.00009665352,0.0009733869,0.005922709],"genre_scores_gemma":[0.9454091,0.000110337,0.0507569,0.0001379521,0.00003141636,0.00006556986,0.00005560513,0.00004554058,0.003387613],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003689416,"threshold_uncertainty_score":0.008072317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04711267251915957,"score_gpt":0.2824716006074344,"score_spread":0.2353589280882748,"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."}}