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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Reinforcement learning is considered to be a strong AI paradigm which can beused to teach machines through interaction with the environment and learningfrom their mistakes, but it has not yet been successfully used for automotiveapplications. There has recently been a revival of interest in the topic,however, driven by the ability of deep learning algorithms to learn goodrepresentations of the environment. Motivated by Google DeepMind's successfuldemonstrations of learning for games from Breakout to Go, we will proposedifferent methods for autonomous driving using deep reinforcement learning.This is of particular interest as it is difficult to pose autonomous driving asa supervised learning problem as it has a strong interaction with theenvironment including other vehicles, pedestrians and roadworks. As this is arelatively new area of research for autonomous driving, we will formulate twomain categories of algorithms: 1) Discrete actions category, and 2) Continuousactions category. For the discrete actions category, we will deal with DeepQ-Network Algorithm (DQN) while for the continuous actions category, we willdeal with Deep Deterministic Actor Critic Algorithm (DDAC). In addition tothat, We will also discover the performance of these two categories on an opensource car simulator for Racing called (TORCS) which stands for The Open Racingcar Simulator. Our simulation results demonstrate learning of autonomousmaneuvering in a scenario of complex road curvatures and simple interactionwith other vehicles. Finally, we explain the effect of some restrictedconditions, put on the car during the learning phase, on the convergence timefor finishing its learning phase.

End-to-End Deep Reinforcement Learning for Lane Keeping Assist