Dynamic Sparse Training For Deep Reinforcement Learning

Abstract

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 agen

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysokar2021dynamic

Related papers

• Learning Sparse Representations Incrementally In Deep Reinforcement Learning (2019)0.00
• Reducing The Deployment-time Inference Control Costs Of Deep Reinforcement Learning Agents Via An Asymmetric Architecture (2021)0.00
• Deep Q-networks For Accelerating The Training Of Deep Neural Networks (2016)0.00
• DQN With Model-based Exploration: Efficient Learning On Environments With Sparse Rewards (2019)0.00
• Dynamic Reinforcement Learning For Actors (2025)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00
• Demonstration-guided Continual Reinforcement Learning In Dynamic Environments (2025)0.00
• Eau De \(q\)-network: Adaptive Distillation Of Neural Networks In Deep Reinforcement Learning (2025)0.00