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

Although deep reinforcement learning (DRL) algorithms have made importantachievements in many control tasks, they still suffer from the problems ofsample inefficiency and unstable training process, which are usually caused bysparse rewards. Recently, some reinforcement learning from demonstration (RLfD)methods have shown to be promising in overcoming these problems. However, theyusually require considerable demonstrations. In order to tackle thesechallenges, on the basis of the SAC algorithm we propose a sample efficientDRL-EG (DRL with efficient guidance) algorithm, in which a discriminator D(s)and a guider G(s) are modeled by a small number of expert demonstrations. Thediscriminator will determine the appropriate guidance states and the guiderwill guide agents to better exploration in the training phase. Empiricalevaluation results from several continuous control tasks verify theeffectiveness and performance improvements of our method over other RL and RLfDcounterparts. Experiments results also show that DRL-EG can help the agent toescape from a local optimum.

Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control