Dynamic Sparse Training for Deep Reinforcement Learning

Ghada Sokar

Elena Mocanu

Decebal Constantin Mocanu

Mykola Pechenizkiy

Peter Stone

IJCAI 2022



Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and memory resources are consumed. Recently, learning efficient DRL agents has received increasing attention. Yet, current methods focus on accelerating inference time. In this paper, we introduce for the first time a dynamic sparse training approach for deep reinforcement learning to accelerate the training process. The proposed approach trains a sparse neural network from scratch and dynamically adapts its topology to the changing data distribution during training. Experiments on continuous control tasks show that our dynamic sparse agents achieve higher performance than the equivalent dense methods, reduce the parameter count and floating-point operations (FLOPs) by 50%, and have a faster learning speed that enables reaching the performance of dense agents with 40-50% reduction in the training steps.

Related Publications

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

NeurIPS, 2022
Bo Liu*, Mao Ye*, Stephen Wright*, Peter Stone, Qiang Liu*

Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning. Conventional BO methods need to differentiate through the…

Value Function Decomposition for Iterative Design of Reinforcement Learning Agents

NeurIPS, 2022
James MacGlashan, Evan Archer, Alisa Devlic, Takuma Seno, Craig Sherstan, Peter R. Wurman, Peter Stone

Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show …

Quantifying Changes in Kinematic Behavior of a Human-Exoskeleton Interactive System

IROS, 2022
Keya Ghonasgi*, Reuth Mirsky*, Adrian M Haith*, Peter Stone, Ashish D Deshpande*

While human-robot interaction studies are becoming more common, quantification of the effects of repeated interaction with an exoskeleton remains unexplored. We draw upon existing literature in human skill assessment and present extrinsic and intrinsic performance metrics t…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.