Log In Sign Up

GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning

by   Juhyoung Lee, et al.

Deep reinforcement learning (DRL) has shown remarkable success in sequential decision-making problems but suffers from a long training time to obtain such good performance. Many parallel and distributed DRL training approaches have been proposed to solve this problem, but it is difficult to utilize them on resource-limited devices. In order to accelerate DRL in real-world edge devices, memory bandwidth bottlenecks due to large weight transactions have to be resolved. However, previous iterative pruning not only shows a low compression ratio at the beginning of training but also makes DRL training unstable. To overcome these shortcomings, we propose a novel weight compression method for DRL training acceleration, named group-sparse training (GST). GST selectively utilizes block-circulant compression to maintain a high weight compression ratio during all iterations of DRL training and dynamically adapt target sparsity through reward-aware pruning for stable training. Thanks to the features, GST achieves a 25 %p ∼ 41.5 %p higher average compression ratio than the iterative pruning method without reward drop in Mujoco Halfcheetah-v2 and Mujoco humanoid-v2 environment with TD3 training.


page 1

page 2

page 3

page 4


Dynamic Sparse Training for Deep Reinforcement Learning

Deep reinforcement learning has achieved significant success in many dec...

Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask

In recent years, a variety of tasks have been accomplished by deep reinf...

PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning

The recent success of deep neural networks (DNNs) for function approxima...

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

Training deep reinforcement learning (DRL) models usually requires high ...

Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression and Challenge

AI heralds a step-change in the performance and capability of wireless n...

Enabling Deep Reinforcement Learning on Energy Constrained Devices at the Edge of the Network

Deep Reinforcement Learning (DRL) solutions are becoming pervasive at th...

Applicability and Challenges of Deep Reinforcement Learning for Satellite Frequency Plan Design

The study and benchmarking of Deep Reinforcement Learning (DRL) models h...