Dynamic Sparse Training for Deep Reinforcement Learning

Dynamic Sparse Training for Deep Reinforcement Learning

Ghada Sokar, Elena Mocanu, Decebal Constantin Mocanu, Mykola Pechenizkiy, Peter Stone

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 3437-3443. https://doi.org/10.24963/ijcai.2022/477

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.
Keywords:
Machine Learning: Deep Reinforcement Learning
Machine Learning: Learning Sparse Models
Machine Learning: Representation learning