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

Deep reinforcement learning (DRL) has been demonstrated to provide promisingresults in several challenging decision making and control tasks. However, therequired inference costs of deep neural networks (DNNs) could prevent DRL frombeing applied to mobile robots which cannot afford high energy-consumingcomputations. To enable DRL methods to be affordable in such energy-limitedplatforms, we propose an asymmetric architecture that reduces the overallinference costs via switching between a computationally expensive policy and aneconomic one. The experimental results evaluated on a number of representativebenchmark suites for robotic control tasks demonstrate that our method is ableto reduce the inference costs while retaining the agent's overall performance.

Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture