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

Marginalized importance sampling (MIS), which measures the density ratiobetween the state-action occupancy of a target policy and that of a samplingdistribution, is a promising approach for off-policy evaluation. However,current state-of-the-art MIS methods rely on complex optimization tricks andsucceed mostly on simple toy problems. We bridge the gap between MIS and deepreinforcement learning by observing that the density ratio can be computed fromthe successor representation of the target policy. The successor representationcan be trained through deep reinforcement learning methodology and decouplesthe reward optimization from the dynamics of the environment, making theresulting algorithm stable and applicable to high-dimensional domains. Weevaluate the empirical performance of our approach on a variety of challengingAtari and MuJoCo environments.

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation