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 reinforcement learning for visual navigation, it is common to develop amodel for each new task, and train that model from scratch with task-specificinteractions in 3D environments. However, this process is expensive; massiveamounts of interactions are needed for the model to generalize well. Moreover,this process is repeated whenever there is a change in the task type or thegoal modality. We present a unified approach to visual navigation using a novelmodular transfer learning model. Our model can effectively leverage itsexperience from one source task and apply it to multiple target tasks (e.g.,ObjectNav, RoomNav, ViewNav) with various goal modalities (e.g., image, sketch,audio, label). Furthermore, our model enables zero-shot experience learning,whereby it can solve the target tasks without receiving any task-specificinteractive training. Our experiments on multiple photorealistic datasets andchallenging tasks show that our approach learns faster, generalizes better, andoutperforms SoTA models by a significant margin.

Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation