Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies

• URL: http://arxiv.org/abs/2508.03194v1
• Date: Tue, 05 Aug 2025 08:03:12 GMT
• Title: Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies
• Authors: Yi Ma, Hongyao Tang, Chenjun Xiao, Yaodong Yang, Wei Wei, Jianye Hao, Jiye Liang,
• Abstract summary: Scaling Laws demonstrate that scaling model parameters and training data enhances learning performance.<n>Despite its potential to improve performance, the integration of scaling laws into deep reinforcement learning has not been fully realized.<n>This review addresses this gap by systematically analyzing scaling strategies in three dimensions: data, network, and training budget.
• Score: 66.83950068218033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, the expansion of neural network models and training data has driven remarkable progress in deep learning, particularly in computer vision and natural language processing. This advancement is underpinned by the concept of Scaling Laws, which demonstrates that scaling model parameters and training data enhances learning performance. While these fields have witnessed breakthroughs, such as the development of large language models like GPT-4 and advanced vision models like Midjourney, the application of scaling laws in deep reinforcement learning (DRL) remains relatively unexplored. Despite its potential to improve performance, the integration of scaling laws into DRL for decision making has not been fully realized. This review addresses this gap by systematically analyzing scaling strategies in three dimensions: data, network, and training budget. In data scaling, we explore methods to optimize data efficiency through parallel sampling and data generation, examining the relationship between data volume and learning outcomes. For network scaling, we investigate architectural enhancements, including monolithic expansions, ensemble and MoE methods, and agent number scaling techniques, which collectively enhance model expressivity while posing unique computational challenges. Lastly, in training budget scaling, we evaluate the impact of distributed training, high replay ratios, large batch sizes, and auxiliary training on training efficiency and convergence. By synthesizing these strategies, this review not only highlights their synergistic roles in advancing DRL for decision making but also provides a roadmap for future research. We emphasize the importance of balancing scalability with computational efficiency and outline promising directions for leveraging scaling to unlock the full potential of DRL in various tasks such as robot control, autonomous driving and LLM training.

Related papers

• Scaling Laws of Motion Forecasting and Planning -- A Technical Report [23.340801154900387]
  We study the empirical scaling laws of a family of encoder-decoder autoregressive transformer models.<n>We observe a strong correlation between model training loss and model evaluation metrics.<n>We briefly study the utility of training on general logged driving data of other agents to improve the performance of the ego-agent.
  arXiv  Detail & Related papers  (2025-06-09T20:54:23Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
  Generative retrieval reformulates retrieval as an autoregressive generation task, where large language models generate target documents directly from a query.<n>We systematically investigate training and inference scaling laws in generative retrieval, exploring how model size, training data scale, and inference-time compute jointly influence performance.
  arXiv  Detail & Related papers  (2025-03-24T17:59:03Z)
• Deep-and-Wide Learning: Enhancing Data-Driven Inference via Synergistic Learning of Inter- and Intra-Data Representations [8.013386998355966]
  Current deep neural network (DNN) models face several challenges, such as the requirements of extensive amounts of data and computational resources.<n>Here, we introduce a new learning scheme, referred to as deep-and-wide learning (DWL), to systematically capture features.<n>We show that DWL surpasses state-of-the-art DNNs in accuracy by a substantial margin with limited training data.
  arXiv  Detail & Related papers  (2025-01-28T23:47:34Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• A Review of Deep Reinforcement Learning in Serverless Computing: Function Scheduling and Resource Auto-Scaling [2.0722667822370386]
  This paper presents a comprehensive review of the application of Deep Reinforcement Learning (DRL) techniques in serverless computing. A systematic review of recent studies applying DRL to serverless computing is presented, covering various algorithms, models, and performances. Our analysis reveals that DRL, with its ability to learn and adapt from an environment, shows promising results in improving the efficiency of function scheduling and resource scaling.
  arXiv  Detail & Related papers  (2023-10-05T09:26:04Z)
• On Efficient Training of Large-Scale Deep Learning Models: A Literature Review [90.87691246153612]
  The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech. The use of large-scale models trained on vast amounts of data holds immense promise for practical applications. With the increasing demands on computational capacity, a comprehensive summarization on acceleration techniques of training deep learning models is still much anticipated.
  arXiv  Detail & Related papers  (2023-04-07T11:13:23Z)
• POAR: Efficient Policy Optimization via Online Abstract State Representation Learning [6.171331561029968]
  State Representation Learning (SRL) is proposed to specifically learn to encode task-relevant features from complex sensory data into low-dimensional states. We introduce a new SRL prior called domain resemblance to leverage expert demonstration to improve SRL interpretations. We empirically verify POAR to efficiently handle tasks in high dimensions and facilitate training real-life robots directly from scratch.
  arXiv  Detail & Related papers  (2021-09-17T16:52:03Z)
• Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training [126.49572353148262]
  We study two factors in neural network training: data parallelism and sparsity. Despite their promising benefits, understanding of their effects on neural network training remains elusive.
  arXiv  Detail & Related papers  (2020-03-25T10:49:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.