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

Imitation learning (IL), aiming to learn optimal control policies from expertdemonstrations, has been an effective method for robot manipulation tasks.However, previous IL methods either only use expensive expert demonstrationsand omit imperfect demonstrations or rely on interacting with the environmentand learning from online experiences. In the context of robotic manipulation,we aim to conquer the above two challenges and propose a novel framework namedSimilarity Weighted Behavior Transformer (SWBT). SWBT effectively learn fromboth expert and imperfect demonstrations without interaction with environments.We reveal that the easy-to-get imperfect demonstrations, such as forward andinverse dynamics, significantly enhance the network by learning fruitfulinformation. To the best of our knowledge, we are the first to attempt tointegrate imperfect demonstrations into the offline imitation learning settingfor robot manipulation tasks. Extensive experiments on the ManiSkill2 benchmarkbuilt on the high-fidelity Sapien simulator and real-world robotic manipulationtasks demonstrated that the proposed method can extract better features andimprove the success rates for all tasks. Our code will be released uponacceptance of the paper.

SWBT: Similarity Weighted Behavior Transformer with the Imperfect Demonstration for Robotic Manipulation