EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Time and Action Co-Training in Reinforcement Learning Agents

Ashlesha Akella, Chin-Teng Lin

Frontiers in Control Engineering · 2021

DOI: 10.3389/fcteg.2021.722092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Control Engineering, 2021. Verfasst von Ashlesha Akella und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In formation control, a robot (or an agent) learns to align itself in a particular spatial alignment. However, in a few scenarios, it is also vital to learn temporal alignment along with spatial alignment. An effective control system encompasses flexibility, precision, and timeliness. Existing reinforcement learning algorithms excel at learning to select an action given a state. However, executing an optimal action at an appropriate time remains challenging. Building a reinforcement learning agent which can learn an optimal time to act along with an optimal action can address this challenge. Neural networks in which timing relies on dynamic changes in the activity of population neurons have been shown to be a more effective representation of time. In this work, we trained a reinforcement learning agent to create its representation of time using a neural network with a population of recurrently connected nonlinear firing rate neurons. Trained using a reward-based recursive least square algorithm, the agent learned to produce a neural trajectory that peaks at the “time-to-act”; thus, it learns “when” to act. A few control system applications also require the agent to temporally scale its action. We trained the agent so that it could temporally scale its action for different speed inputs. Furthermore, given one state, the agent could learn to plan multiple future actions, that is, multiple times to act without needing to observe a new state.

Zitieren

APA

Akella, A., & Lin, C. (2021). Time and Action Co-Training in Reinforcement Learning Agents. Frontiers in Control Engineering. https://doi.org/10.3389/fcteg.2021.722092

Vancouver

Akella A, Lin C. Time and Action Co-Training in Reinforcement Learning Agents. Frontiers in Control Engineering. 2021. doi:10.3389/fcteg.2021.722092

BibTeX
@article{Akella2021,
  author = {Akella, Ashlesha and Lin, Chin-Teng},
  title = {Time and Action Co-Training in Reinforcement Learning Agents},
  journal = {Frontiers in Control Engineering},
  year = {2021},
  doi = {10.3389/fcteg.2021.722092}
}
Kostenlos starten →