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/

Zendy Plus

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

Zendy Tools

Zendy Open

An effective way to achieve intelligence is to simulate various intelligentbehaviors in the human brain. In recent years, bio-inspired learning methodshave emerged, and they are different from the classical mathematicalprogramming principle. In the perspective of brain inspiration, reinforcementlearning has gained additional interest in solving decision-making tasks asincreasing neuroscientific research demonstrates that significant links existbetween reinforcement learning and specific neural substrates. Because of thetremendous research that focuses on human brains and reinforcement learning,scientists have investigated how robots can autonomously tackle complex tasksin the form of a self-driving agent control in a human-like way. In this study,we propose an end-to-end architecture using novel deep-Q-network architecturein conjunction with a recurrence to resolve the problem in the field ofsimulated self-driving. The main contribution of this study is that we trainedthe driving agent using a brain-inspired trial-and-error technique, which wasin line with the real world situation. Besides, there are three innovations inthe proposed learning network: raw screen outputs are the only informationwhich the driving agent can rely on, a weighted layer that enhances thedifferences of the lengthy episode, and a modified replay mechanism thatovercomes the problem of sparsity and accelerates learning. The proposednetwork was trained and tested under a third-partied OpenAI Gym environment.After training for several episodes, the resulting driving agent performedadvanced behaviors in the given scene. We hope that in the future, the proposedbrain-inspired learning system would inspire practicable self-driving controlsolutions.

Towards Brain-inspired System: Deep Recurrent Reinforcement Learning for Simulated Self-driving Agent