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

In this paper, we continue our prior work on using imitation learning (IL)and model free reinforcement learning (RL) to learn driving policies forautonomous driving in urban scenarios, by introducing a model based RL methodto drive the autonomous vehicle in the Carla urban driving simulator. AlthoughIL and model free RL methods have been proved to be capable of solving lots ofchallenging tasks, including playing video games, robots, and, in our priorwork, urban driving, the low sample efficiency of such methods greatly limitstheir applications on actual autonomous driving. In this work, we developed amodel based RL algorithm of guided policy search (GPS) for urban driving tasks.The algorithm iteratively learns a parameterized dynamic model to approximatethe complex and interactive driving task, and optimizes the driving policyunder the nonlinear approximate dynamic model. As a model based RL approach,when applied in urban autonomous driving, the GPS has the advantages of highersample efficiency, better interpretability, and greater stability. We provideextensive experiments validating the effectiveness of the proposed method tolearn robust driving policy for urban driving in Carla. We also compare theproposed method with other policy search and model free RL baselines, showing100x better sample efficiency of the GPS based RL method, and also that the GPSbased method can learn policies for harder tasks that the baseline methods canhardly learn.

Guided Policy Search Model-based Reinforcement Learning for Urban Autonomous Driving