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 this paper, we study the global convergence of model-based and model-freepolicy gradient descent and natural policy gradient descent algorithms forlinear quadratic deep structured teams. In such systems, agents are partitionedinto a few sub-populations wherein the agents in each sub-population arecoupled in the dynamics and cost function through a set of linear regressionsof the states and actions of all agents. Every agent observes its local stateand the linear regressions of states, called deep states. For a sufficientlysmall risk factor and/or sufficiently large population, we prove thatmodel-based policy gradient methods globally converge to the optimal solution.Given an arbitrary number of agents, we develop model-free policy gradient andnatural policy gradient algorithms for the special case of risk-neutral costfunction. The proposed algorithms are scalable with respect to the number ofagents due to the fact that the dimension of their policy space is independentof the number of agents in each sub-population. Simulations are provided toverify the theoretical results.

Reinforcement Learning in Linear Quadratic Deep Structured Teams: Global Convergence of Policy Gradient Methods