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

Applications of reinforcement learning (RL) are popular in autonomous drivingtasks. That being said, tuning the performance of an RL agent and guaranteeingthe generalization performance across variety of different driving scenarios isstill largely an open problem. In particular, getting good performance oncomplex road and weather conditions require exhaustive tuning and computationtime. Curriculum RL, which focuses on solving simpler automation tasks in orderto transfer knowledge to complex tasks, is attracting attention in RLcommunity. The main contribution of this paper is a systematic study forinvestigating the value of curriculum reinforcement learning in autonomousdriving applications. For this purpose, we setup several different drivingscenarios in a realistic driving simulator, with varying road complexity andweather conditions. Next, we train and evaluate performance of RL agents ondifferent sequences of task combinations and curricula. Results show thatcurriculum RL can yield significant gains in complex driving tasks, both interms of driving performance and sample complexity. Results also demonstratethat different curricula might enable different benefits, which hints futureresearch directions for automated curriculum training.

Investigating Value of Curriculum Reinforcement Learning in Autonomous Driving Under Diverse Road and Weather Conditions