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

Learning to solve long horizon temporally extended tasks with reinforcementlearning has been a challenge for several years now. We believe that it isimportant to leverage both the hierarchical structure of complex tasks and touse expert supervision whenever possible to solve such tasks. This workintroduces an interpretable hierarchical agent framework by combining planningand semantic goal directed reinforcement learning. We assume access to certainspatial and haptic predicates and construct a simple and powerful semantic goalspace. These semantic goal representations are more interpretable, makingexpert supervision and intervention easier. They also eliminate the need towrite complex, dense reward functions thereby reducing human engineeringeffort. We evaluate our framework on a robotic block manipulation task and showthat it performs better than other methods, including both sparse and densereward functions. We also suggest some next steps and discuss how thisframework makes interaction and collaboration with humans easier.

Towards an Interpretable Hierarchical Agent Framework using Semantic Goals