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

Robotic insertion tasks are characterized by contact and friction mechanics,making them challenging for conventional feedback control methods due tounmodeled physical effects. Reinforcement learning (RL) is a promising approachfor learning control policies in such settings. However, RL can be unsafeduring exploration and might require a large amount of real-world trainingdata, which is expensive to collect. In this paper, we study how to usemeta-reinforcement learning to solve the bulk of the problem in simulation bysolving a family of simulated industrial insertion tasks and then adaptpolicies quickly in the real world. We demonstrate our approach by training anagent to successfully perform challenging real-world insertion tasks using lessthan 20 trials of real-world experience. Videos and other material areavailable at https://pearl-insertion.github.io/

Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks