Verschure, Paul F. M. J.Freire, Ismael T.Amil, Adrián F.Vouloutsi, Vasiliki2023-03-012023-03-012021Freire IT, Amil AF, Vouloutsi V, Verschure PFMJ. Towards sample-efficient policy learning with DAC-ML. Procedia Comput Sci. 2021;190:256–62. DOI: 10.1016/j.procs.2021.06.0351877-0509http://hdl.handle.net/10230/55998The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes. Recent studies have tried to overcome this limitation by adding memory systems and architectural biases to improve learning speed, such as in Episodic Reinforcement Learning. However, despite achieving incremental improvements, their performance is still not comparable to how humans learn behavioral policies. In this paper, we capitalize on the design principles of the Distributed Adaptive Control (DAC) theory of mind and brain to build a novel cognitive architecture (DAC-ML) that, by incorporating a hippocampus-inspired sequential memory system, can rapidly converge to effective action policies that maximize reward acquisition in a challenging foraging task.application/pdfeng© 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)info:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.procs.2021.06.035cognitive architecturesample-inefficiency problemsequence learningreinforcement learningdistributed adaptive controlinfo:eu-repo/semantics/openAccess