Compute-Optimal Scaling for Value-Based Deep RL

• URL: http://arxiv.org/abs/2508.14881v2
• Date: Mon, 25 Aug 2025 05:37:55 GMT
• Title: Compute-Optimal Scaling for Value-Based Deep RL
• Authors: Preston Fu, Oleh Rybkin, Zhiyuan Zhou, Michal Nauman, Pieter Abbeel, Sergey Levine, Aviral Kumar,
• Abstract summary: We investigate compute scaling for online, value-based deep RL.<n>Our analysis reveals a nuanced interplay between model size, batch size, and UTD.<n>We provide a mental model for understanding this phenomenon and build guidelines for choosing batch size and UTD.
• Score: 99.680827753493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As models grow larger and training them becomes expensive, it becomes increasingly important to scale training recipes not just to larger models and more data, but to do so in a compute-optimal manner that extracts maximal performance per unit of compute. While such scaling has been well studied for language modeling, reinforcement learning (RL) has received less attention in this regard. In this paper, we investigate compute scaling for online, value-based deep RL. These methods present two primary axes for compute allocation: model capacity and the update-to-data (UTD) ratio. Given a fixed compute budget, we ask: how should resources be partitioned across these axes to maximize sample efficiency? Our analysis reveals a nuanced interplay between model size, batch size, and UTD. In particular, we identify a phenomenon we call TD-overfitting: increasing the batch quickly harms Q-function accuracy for small models, but this effect is absent in large models, enabling effective use of large batch size at scale. We provide a mental model for understanding this phenomenon and build guidelines for choosing batch size and UTD to optimize compute usage. Our findings provide a grounded starting point for compute-optimal scaling in deep RL, mirroring studies in supervised learning but adapted to TD learning.

Related papers

• Scaling Laws of Global Weather Models [57.27583619011988]
  We investigate the relationship between model performance (validation loss) and three key factors: model size, dataset size, and compute budget.<n>Across a range of models, we find that Aurora exhibits the strongest data-scaling behavior.<n>Our compute-optimal analysis indicates that, under fixed compute budgets, allocating resources to longer training durations yields greater performance gains than increasing model size.
  arXiv  Detail & Related papers  (2026-02-26T12:57:38Z)
• Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size? [12.791994483385409]
  Concerns are growing about the depletion of high-quality, well-curated training data.<n>The decentralization of training datasets in Federated Learning introduces challenges to scaling large models.<n>This paper provides insights on generalizing the previous model scaling experience to federated learning scenarios.
  arXiv  Detail & Related papers  (2025-11-15T12:41:25Z)
• Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies [66.83950068218033]
  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.
  arXiv  Detail & Related papers  (2025-08-05T08:03:12Z)
• Intention-Conditioned Flow Occupancy Models [80.42634994902858]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• 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)
• Value-Based Deep RL Scales Predictably [100.21834069400023]
  We show that value-based off-policy RL methods are predictable despite community lore regarding their pathological behavior.<n>We validate our approach using three algorithms: SAC, BRO, and PQL on DeepMind Control, OpenAI gym, and IsaacGym.
  arXiv  Detail & Related papers  (2025-02-06T18:59:47Z)
• More Compute Is What You Need [3.184416958830696]
  We propose a new scaling law that suggests model performance depends mostly on the amount of compute spent for transformer-based models. We predict that (a) for inference efficiency, training should prioritize smaller model sizes and larger training datasets, and (b) assuming the exhaustion of available web datasets, scaling the model size might be the only way to further improve model performance.
  arXiv  Detail & Related papers  (2024-04-30T12:05:48Z)
• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Scaling Laws for Neural Language Models [14.472857826717613]
  We study scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training.
  arXiv  Detail & Related papers  (2020-01-23T03:59:20Z)

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.