2018
DOI: 10.1016/j.cogsys.2018.04.014
|View full text |Cite
|
Sign up to set email alerts
|

A working memory model improves cognitive control in agents and robots

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 12 publications
(5 citation statements)
references
References 18 publications
0
5
0
Order By: Relevance
“…Although the aim of this approach was primarily to increase the learning performance of the agents, compared to an uniform sampling baseline the entropybased sampling also seemed to have induced an intrinsically motivated exploration that became an important part of their tactics to increase the overall performance. Persiani et al [28] introduces an approach that also uses the replay memory structure in order to improve cognition. The algorithm is able to actively learn to select the most appropriate chunks of the agent's experience to be stored in the replay memory buffer based on maximizing the expected future reward.…”
Section: B Artificial Attention As a Behavior Inducing Mechanismmentioning
confidence: 99%
“…Although the aim of this approach was primarily to increase the learning performance of the agents, compared to an uniform sampling baseline the entropybased sampling also seemed to have induced an intrinsically motivated exploration that became an important part of their tactics to increase the overall performance. Persiani et al [28] introduces an approach that also uses the replay memory structure in order to improve cognition. The algorithm is able to actively learn to select the most appropriate chunks of the agent's experience to be stored in the replay memory buffer based on maximizing the expected future reward.…”
Section: B Artificial Attention As a Behavior Inducing Mechanismmentioning
confidence: 99%
“…There has also been significant work in robotics seeking to use insights from psychological research on WM to better inform the design of select components of larger robot cognitive architectures that do not necessarily aspire towards cognitive plausibility. For example, a diverse body of researchers has collaborated on the development and use of the WM Toolkit (Phillips & Noelle, 2005;Gordon & Hall, 2006;Kawamura et al, 2008;Persiani et al, 2018); a software toolkit that maintains pointers to a fixed number of chunks containing arbitrary information. At each timestep, this toolkit proposes a new set of chunks, and then uses neural networks to select a subset of these chunks to retain.…”
Section: Models Of Working Memory In Integrated Robot Architecturesmentioning
confidence: 99%
“…Persiani et al [19] proposes a cognitive improvement through the use of replay memory structure like AMR. The algorithm makes it possible to learn which chunks of agent's experiences are most appropriate for replay based on their ability to maximize the future expected reward.…”
Section: Related Workmentioning
confidence: 99%