Carregant...
Tipus de document
AltresVersió
Versió publicadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/182959
Towards sample-efficient policy learning with DAC-ML
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
The 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.
Matèries
Matèries (anglès)
Citació
Citació
FREIRE, Ismael t., AMIL, Adrián f., VOULOUTSI, Vasiliki, VERSCHURE, Paul f. m. j.. Towards sample-efficient policy learning with DAC-ML. _Procedia Computer Science_. 2021. Vol. vol 190, núm. 256-262. [consulta: 25 de febrer de 2026]. ISSN: Freire IT;Amil AF;Vouloutsi V;Verschure PFMJ. Towards sample-efficient policy learning with DAC-ML. Procedia Computer Science, 2021, 190, 256-262. [Disponible a: https://hdl.handle.net/2445/182959]