English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep reinforcement learning has been applied more and more widely nowadays,especially in various complex control tasks. Effective exploration for noisynetworks is one of the most important issues in deep reinforcement learning.Noisy networks tend to produce stable outputs for agents. However, thistendency is not always enough to find a stable policy for an agent, whichdecreases efficiency and stability during the learning process. Based onNoisyNets, this paper proposes an algorithm called NROWAN-DQN, i.e., NoiseReduction and Online Weight Adjustment NoisyNet-DQN. Firstly, we develop anovel noise reduction method for NoisyNet-DQN to make the agent perform stableactions. Secondly, we design an online weight adjustment strategy for noisereduction, which improves stable performance and gets higher scores for theagent. Finally, we evaluate this algorithm in four standard domains and analyzeproperties of hyper-parameters. Our results show that NROWAN-DQN outperformsprior algorithms in all these domains. In addition, NROWAN-DQN also showsbetter stability. The variance of the NROWAN-DQN score is significantlyreduced, especially in some action-sensitive environments. This means that insome environments where high stability is required, NROWAN-DQN will be moreappropriate than NoisyNets-DQN.

NROWAN-DQN: A Stable Noisy Network with Noise Reduction and Online Weight Adjustment for Exploration