paper-with-me

홈 › Papers

Dynamic Sparse Training for Deep Reinforcement Learning

2021-06-08 · Ghada Sokar, Elena Mocanu, Decebal Constantin Mocanu, Mykola Pechenizkiy, Peter Stone

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.

📄 PDF Abstract BibTeX arXiv:2106.04217

Code (1)

GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlDecision MakingDeep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning

2025-10-14 · Guozheng Ma, Lu Li, Zilin Wang, Haoyu Wang 외 arxiv

Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade performance due to unique optimization patholo…

Reinforcement Learning

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

2022-05-30 · Yiqin Tan, Pihe Hu, Ling Pan, Jiatai Huang 외

Training deep reinforcement learning (DRL) models usually requires high computation costs. Therefore, compressing DRL models possesses immense potential for training acceleration and model deployment. However, existing m…

Continuous ControlDeep Reinforcement LearningKnowledge DistillationModel Compression+3

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

2024-09-28 · Pihe Hu, Shaolong Li, Zhuoran Li, Ling Pan 외

Deep Multi-agent Reinforcement Learning (MARL) relies on neural networks with numerous parameters in multi-agent scenarios, often incurring substantial computational overhead. Consequently, there is an urgent need to exp…

Model CompressionMulti-agent Reinforcement Learning

Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks

2025-11-11 · Muthukumar Pandaram, Jakob Hollenstein, David Drexel, Samuele Tosatto 외 arxiv

The use of learned dynamics models, also known as world models, can improve the sample efficiency of reinforcement learning. Recent work suggests that the underlying causal graphs of such dynamics models are sparsely con…

Reinforcement Learning

Topology-Aware Revival for Efficient Sparse Training

2026-02-04 · Meiling Jin, Fei Wang, Xiaoyun Yuan, Chen Qian 외 arxiv

Static sparse training is a promising route to efficient learning by committing to a fixed mask pattern, yet the constrained structure reduces robustness. Early pruning decisions can lock the network into a brittle struc…

Reinforcement Learning