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

Reinforcement Learning (RL) can enable agents to learn complex tasks.However, it is difficult to interpret the knowledge and reuse it across tasks.Inductive biases can address such issues by explicitly providing generic yetuseful decomposition that is otherwise difficult or expensive to learnimplicitly. For example, object-centered approaches decompose a highdimensional observation into individual objects. Expanding on this, we utilizean inductive bias for explicit object-centered knowledge separation thatprovides further decomposition into semantic representations and dynamicsknowledge. For this, we introduce a semantic module that predicts an objects'semantic state based on its context. The resulting affordance-like object statecan then be used to enrich perceptual object representations. With a minimalsetup and an environment that enables puzzle-like tasks, we demonstrate thefeasibility and benefits of this approach. Specifically, we compare threedifferent methods of integrating semantic representations into a model-based RLarchitecture. Our experiments show that the degree of explicitness in knowledgeseparation correlates with faster learning, better accuracy, bettergeneralization, and better interpretability.

Relate to Predict: Towards Task-Independent Knowledge Representations for Reinforcement Learning