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

Deep Reinforcement Learning (DRL) has exhibited efficacy in resolving theLocal Path Planning (LPP) problem. However, such application in the real worldis immensely limited due to the deficient training efficiency andgeneralization capability of DRL. To alleviate these two issues, a solutionnamed Color is proposed, which consists of an Actor-Sharer-Learner (ASL)training framework and a mobile robot-oriented simulator Sparrow. Specifically,the ASL intends to improve the training efficiency of DRL algorithms. Itemploys a Vectorized Data Collection (VDC) mode to expedite data acquisition,decouples the data collection from model optimization by multithreading, andpartially connects the two procedures by harnessing a Time Feedback Mechanism(TFM) to evade data underuse or overuse. Meanwhile, the Sparrow simulatorutilizes a 2D grid-based world, simplified kinematics, and conversion-free dataflow to achieve a lightweight design. The lightness facilitates vectorizeddiversity, allowing diversified simulation setups across extensive copies ofthe vectorized environments, resulting in a notable enhancement in thegeneralization capability of the DRL algorithm being trained. Comprehensiveexperiments, comprising 57 DRL benchmark environments, 32 simulated and 36real-world LPP scenarios, have been conducted to corroborate the superiority ofour method in terms of efficiency and generalization. The code and the video ofthis paper are accessible at https://github.com/XinJingHao/Color.

Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity