Ensemble Network Architecture for Deep Reinforcement Learning

Xi-liang Chen, Lei Cao, Chen-xi Li, Zhi-xiong Xu and Jun Lai

Mathematical Problems in Engineering, 2018, vol. 2018, 1-6

Abstract:

The popular deep learning algorithm is known to be instability because of the -value’s shake and overestimation action values under certain conditions. These issues tend to adversely affect their performance. In this paper, we develop the ensemble network architecture for deep reinforcement learning which is based on value function approximation. The temporal ensemble stabilizes the training process by reducing the variance of target approximation error and the ensemble of target values reduces the overestimate and makes better performance by estimating more accurate -value. Our results show that this architecture leads to statistically significant better value evaluation and more stable and better performance on several classical control tasks at OpenAI Gym environment.

Date: 2018
References: Add references at CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://downloads.hindawi.com/journals/MPE/2018/2129393.pdf (application/pdf)
http://downloads.hindawi.com/journals/MPE/2018/2129393.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:2129393

DOI: 10.1155/2018/2129393

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().