{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004107275,0.0004212589,0.0005863919,0.00131721,0.001472352,0.001192254,0.001076204,0.000261027,0.00003896784],"category_scores_gemma":[0.005200153,0.0003865425,0.0001796693,0.00202568,0.000371477,0.000574852,0.0008893273,0.001199908,0.0001809528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005551752,"about_ca_system_score_gemma":0.001881632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001125211,"about_ca_topic_score_gemma":0.000007330068,"domain_scores_codex":[0.9938876,0.001203827,0.0008647979,0.001129712,0.001390408,0.001523655],"domain_scores_gemma":[0.9882483,0.006945475,0.0002920692,0.0005477358,0.003697562,0.0002688199],"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":[0.0004289918,0.00007544095,0.0003554369,0.0005905496,0.0002753533,0.00009291891,0.0009713743,0.9693543,0.0002322791,0.01859556,0.0007797305,0.008248013],"study_design_scores_gemma":[0.003459194,0.001312612,0.0001914202,0.002303271,0.00004396985,0.000009928359,0.003299302,0.9825447,0.002901728,0.00005761797,0.003415835,0.0004603961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009813146,0.0002340795,0.9706558,0.0003150224,0.0007831065,0.003678886,0.000006104076,0.0003772663,0.02296843],"genre_scores_gemma":[0.9574316,0.00002772209,0.004559175,0.0001731941,0.0001749466,0.001248479,0.00009610111,0.00004955776,0.03623927],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9660966,"threshold_uncertainty_score":0.9998587,"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."}}