Robustness and performance of Deep Reinforcement Learning

Raid Rafi Omar Al-Nima*, Tingting Han, Saadoon Awad Mohammed Al-Sumaidaee, Taolue Chen, Wai Lok Woo

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Deep Reinforcement Learning (DRL) has recently obtained considerable attentions. It empowers Reinforcement Learning (RL) with Deep Learning (DL) techniques to address various difficult tasks. In this paper, a novel approach called the Genetic Algorithm of Neuron Coverage (GANC) is proposed. It is motivated for improving the robustness and performance of a DRL network. The GANC uses Genetic Algorithm (GA) to maximise the Neuron Coverage (NC) of a DRL network by producing augmented inputs. We apply this method in the self-driving car applications, where it is crucial to accurately provide a correct decision for different road tracking views. We evaluate our method on the SYNTHIA-SEQS-05 databases in four different driving environments. Our outcomes are very promising – the best driving accuracy reached 97.75% – and are superior to the state-of-the-art results.
Original languageEnglish
Article number107295
Number of pages12
JournalApplied Soft Computing
Volume105
Early online date16 Mar 2021
DOIs
Publication statusPublished - 1 Jul 2021

Fingerprint

Dive into the research topics of 'Robustness and performance of Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this