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

Not until recently, robust robot locomotion has been achieved by deepreinforcement learning (DRL). However, for efficient learning of parametrizedbipedal walking, developed references are usually required, limiting theperformance to that of the references. In this paper, we propose to design anadaptive reward function for imitation learning from the references. The agentis encouraged to mimic the references when its performance is low, while topursue high performance when it reaches the limit of references. We furtherdemonstrate that developed references can be replaced by low-quality referencesthat are generated without laborious tuning and infeasible to deploy bythemselves, as long as they can provide a priori knowledge to expedite thelearning process.

Adaptive Mimic: Deep Reinforcement Learning of Parameterized Bipedal Walking from Infeasible References