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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Combining model-based and model-free learning systems has been shown toimprove the sample efficiency of learning to perform complex robotic tasks.However, dual-system approaches fail to consider the reliability of the learnedmodel when it is applied to make multiple-step predictions, resulting in acompounding of prediction errors and performance degradation. In this paper, wepresent a novel dual-system motor learning approach where a meta-controllerarbitrates online between model-based and model-free decisions based on anestimate of the local reliability of the learned model. The reliabilityestimate is used in computing an intrinsic feedback signal, encouraging actionsthat lead to data that improves the model. Our approach also integratesarbitration with imagination where a learned latent-space model generatesimagined experiences, based on its local reliability, to be used as additionaltraining data. We evaluate our approach against baseline and state-of-the-artmethods on learning vision-based robotic grasping in simulation and real world.The results show that our approach outperforms the compared methods and learnsnear-optimal grasping policies in dense- and sparse-reward environments.

Improving Robot Dual-System Motor Learning with Intrinsically Motivated Meta-Control and Latent-Space Experience Imagination