paper-with-me

홈 › Papers

Small batch deep reinforcement learning

2023-10-05 · NeurIPS 2023 11

In value-based deep reinforcement learning with replay memories, the batch size parameter specifies how many transitions to sample for each gradient update. Although critical to the learning process, this value is typically not adjusted when proposing new algorithms. In this work we present a broad empirical study that suggests {\em reducing} the batch size can result in a number of significant performance gains; this is surprising, as the general tendency when training neural networks is towards larger batch sizes for improved performance. We complement our experimental findings with a set of empirical analyses towards better understanding this phenomenon.

📄 PDF Abstract BibTeX arXiv:2310.03882

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Smaller Batches, Bigger Gains? Investigating the Impact of Batch Sizes on Reinforcement Learning Based Real-World Production Scheduling

2024-06-04 · Arthur Müller, Felix Grumbach, Matthia Sabatelli

Production scheduling is an essential task in manufacturing, with Reinforcement Learning (RL) emerging as a key solution. In a previous work, RL was utilized to solve an extended permutation flow shop scheduling problem …

Reinforcement Learning (RL)Scheduling

Switching the Loss Reduces the Cost in Batch Reinforcement Learning

2024-03-08 · Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson 외

We propose training fitted Q-iteration with log-loss (FQI-LOG) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-LOG scales with the accumulated cost…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Distilling Reinforcement Learning into Single-Batch Datasets

2025-08-12 · Connor Wilhelm, Dan Ventura arxiv

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as l…

Reinforcement LearningAtari Games

Scalable Reinforcement Learning via Adaptive Batch Scaling

2026-05-20 · Jongchan Park arxiv

Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increasing batch sizes typically yields diminishing returns or performance d…

Reinforcement Learning

Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints

2021-01-06 · NeurIPS 2021 12 · Tianhao Wang, Dongruo Zhou, Quanquan Gu

We study reinforcement learning (RL) with linear function approximation under the adaptivity constraint. We consider two popular limited adaptivity models: the batch learning model and the rare policy switch model, and p…

reinforcement-learningReinforcement Learning (RL)