{"id":"W4416828434","doi":"10.1016/j.cogsys.2025.101422","title":"Dual or unified: optimizing drive-based reinforcement learning for cognitive autonomous robots","year":2025,"lang":"en","type":"article","venue":"Cognitive Systems Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministério da Ciência, Tecnologia e Inovação; Ministério da Ciência, Tecnologia, Inovações e Comunicações; Fundação de Amparo à Pesquisa do Estado de São Paulo; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Brazilian Institute of Neuroscience and Neurotechnology","keywords":"Reinforcement learning; Modular design; Dual (grammatical number); Cognition; Curiosity; Selection (genetic algorithm); Robot; Autonomous agent; Action selection","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":[0.001391404,0.000893518,0.001255991,0.0004027481,0.0004215968,0.0009508038,0.001783544,0.001312259,0.00275694],"category_scores_gemma":[0.003734657,0.0005540649,0.0004870336,0.0003302522,0.001161971,0.001237266,0.001923896,0.001503662,0.0003457994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007783581,"about_ca_system_score_gemma":0.001273464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003820382,"about_ca_topic_score_gemma":0.004327426,"domain_scores_codex":[0.999588,0.0001262029,0.00001890515,0.00008332901,0.00009856253,0.00008506593],"domain_scores_gemma":[0.9989865,0.0004946681,0.000101097,0.0001154975,0.000196553,0.0001056449],"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":[0.0003103782,0.0001586895,0.0006394901,0.0001164379,0.00007270984,0.00007774826,0.00009802503,0.9103644,0.002654496,0.01870407,0.001617558,0.065186],"study_design_scores_gemma":[0.00001685117,0.00005037014,0.00004497462,0.000003985095,0.000006261296,0.000006110248,0.000004002673,0.9943224,0.0002602409,0.005116531,0.0001646188,0.000003606254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04939949,0.0003479618,0.9438468,0.0002718427,0.00009982135,0.00007382079,0.00004495561,0.0005772946,0.005337893],"genre_scores_gemma":[0.9209304,0.0001012904,0.07568845,0.0001269898,0.00003929314,0.0001256359,0.00004619018,0.00007309167,0.002868501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003820382,"threshold_uncertainty_score":0.009222925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1068081383371196,"score_gpt":0.3925307955731251,"score_spread":0.2857226572360055,"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."}}