Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific Research

ICLR 2024 Workshop DMLR Submission34 Authors

Published: 04 Mar 2024, Last Modified: 02 May 2024DMLR @ ICLR 2024EveryoneRevisionsBibTeXCC BY 4.0
Keywords: data throughput, reinforcement learning, gpu acceleration, data-driven science
TL;DR: a domain agnostic framework designed to overcome crucial system bottlenecks encountered in the application of reinforcement learning to intricate environments with vast datasets
Abstract: We introduce $WarpSci$, a domain agnostic framework designed to overcome crucial system bottlenecks encountered in the application of reinforcement learning to intricate environments with vast datasets featuring high-dimensional observation or action spaces. Notably, our framework eliminates the need for data transfer between the CPU and GPU, enabling the concurrent execution of thousands of simulations on a single or multiple GPUs. This high data throughput architecture proves particularly advantageous for data-driven scientific research, where intricate environment models are commonly essential.
Primary Subject Area: Other
Paper Type: Extended abstracts: up to 2 pages
DMLR For Good Track: Participate in DMLR for Good Track
Participation Mode: Virtual
Confirmation: I have read and agree with the workshop's policy on behalf of myself and my co-authors.
Submission Number: 34
Loading