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

In this work, we analyze the performance of general deep reinforcementlearning algorithms for a task-oriented language grounding problem, wherelanguage input contains multiple sub-goals and their order of execution isnon-linear.  We generate a simple instructional language for the GridWorld environment,that is built around three language elements (order connectors) defining theorder of execution: one linear - "comma" and two non-linear - "but first", "butbefore". We apply one of the deep reinforcement learning baselines - Double DQNwith frame stacking and ablate several extensions such as PrioritizedExperience Replay and Gated-Attention architecture.  Our results show that the introduction of non-linear order connectorsimproves the success rate on instructions with a higher number of sub-goals in2-3 times, but it still does not exceed 20%. Also, we observe that the usage ofGated-Attention provides no competitive advantage against concatenation in thissetting. Source code and experiments' results are available athttps://github.com/vkurenkov/language-grounding-multigoal

Task-Oriented Language Grounding for Language Input with Multiple Sub-Goals of Non-Linear Order