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

The accurate modeling of dynamics in interactive environments is critical forsuccessful long-range prediction. Such a capability could advance ReinforcementLearning (RL) and Planning algorithms, but achieving it is challenging.Inaccuracies in model estimates can compound, resulting in increased errorsover long horizons. We approach this problem from the lens of Koopman theory,where the nonlinear dynamics of the environment can be linearized in ahigh-dimensional latent space. This allows us to efficiently parallelize thesequential problem of long-range prediction using convolution while accountingfor the agent's action at every time step. Our approach also enables stabilityanalysis and better control over gradients through time. Taken together, theseadvantages result in significant improvement over the existing approaches, bothin the efficiency and the accuracy of modeling dynamics over extended horizons.We also show that this model can be easily incorporated into dynamics modelingfor model-based planning and model-free RL and report promising experimentalresults.

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory