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

We consider constrained policy optimization in Reinforcement Learning, wherethe constraints are in form of marginals on state visitations and global actionexecutions. Given these distributions, we formulate policy optimization asunbalanced optimal transport over the space of occupancy measures. We propose ageneral purpose RL objective based on Bregman divergence and optimize it usingDykstra's algorithm. The approach admits an actor-critic algorithm for when thestate or action space is large, and only samples from the marginals areavailable. We discuss applications of our approach and provide demonstrationsto show the effectiveness of our algorithm.

Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport