The coupling of deep reinforcement learning to numerical flow control problems has recently received a considerable attention, leading to groundbreaking results and opening new perspectives for the domain. Due to the usually high computational cost of fluid dynamics solvers, the use of parallel environments during the learning process represents an essential ingredient to attain efficient control in a reasonable time. Yet, most of the deep reinforcement learning literature for flow control relies on on-policy algorithms, for which the massively parallel transition collection may break theoretical assumptions and lead to suboptimal control models. To overcome this issue, we propose a parallelism pattern relying on partial-trajectory buffers terminated by a return bootstrapping step, allowing a flexible use of parallel environments while preserving the on-policiness of the updates. This approach is illustrated on a CPU-intensive continuous flow control problem from the literature.

By clicking Subscribe, you confirm that you have read and agree to our Terms of Use and acknowledge our Privacy Policy and you agree to receive marketing communications, updates, special offers (including partner offers) and other information from South Park and the Paramount family of companies. You understand that you can unsubscribe at any time. A.W.E.S.O.M.- O will not make fun of you or tell your secrets to other people or stuff.

In this episode of SaugaTalks, hosted by Irene Lyakovetsky, I met Stu Bailey, Co-founder and Chief Enterprise AI Architect at ModelOp, to discuss why #ModelOps is a Critical Piece of Enterprise AI Strategy. It is not surprising seeing why #ModelOps is the cornerstone of every #AI initiative. Technology Talk Host: SaugaTalks Chats With Fascinating People In Tech! Follow: bit.ly/SaugaTalksLI and Subscribe For The Full Episodes: bit.ly/SaugaTalks "#ModelOps is a Key #Enterprise Capability for End-to-end #Governance of #AI Initiatives Across the Organization" #SaugaTalks with Giuliano Liguori, Digital Transformation Leader, Innovation Manager, Thought Leader, Board Member CIO Club IT and Stu Bailey, Co-founder and Chief Enterprise AI Architect at ModelOp Full Episode: https://lnkd.in/eVAxm_mt