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

Imitation learning (IL) is a simple and powerful way to use high-qualityhuman driving data, which can be collected at scale, to produce human-likebehavior. However, policies based on imitation learning alone often fail tosufficiently account for safety and reliability concerns. In this paper, weshow how imitation learning combined with reinforcement learning using simplerewards can substantially improve the safety and reliability of drivingpolicies over those learned from imitation alone. In particular, we train apolicy on over 100k miles of urban driving data, and measure its effectivenessin test scenarios grouped by different levels of collision likelihood. Ouranalysis shows that while imitation can perform well in low-difficultyscenarios that are well-covered by the demonstration data, our proposedapproach significantly improves robustness on the most challenging scenarios(over 38% reduction in failures). To our knowledge, this is the firstapplication of a combined imitation and reinforcement learning approach inautonomous driving that utilizes large amounts of real-world human drivingdata.

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios