Online Training and Pruning of Deep Reinforcement Learning Networks

• URL: http://arxiv.org/abs/2507.11975v1
• Date: Wed, 16 Jul 2025 07:17:41 GMT
• Title: Online Training and Pruning of Deep Reinforcement Learning Networks
• Authors: Valentin Frank Ingmar Guenter, Athanasios Sideris,
• Abstract summary: Scaling deep neural networks (NN) of reinforcement learning (RL) algorithms has been shown to enhance performance when feature extraction networks are used.<n>We propose an approach to integrate simultaneous training and pruning within advanced RL methods.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scaling deep neural networks (NN) of reinforcement learning (RL) algorithms has been shown to enhance performance when feature extraction networks are used but the gained performance comes at the significant expense of increased computational and memory complexity. Neural network pruning methods have successfully addressed this challenge in supervised learning. However, their application to RL is underexplored. We propose an approach to integrate simultaneous training and pruning within advanced RL methods, in particular to RL algorithms enhanced by the Online Feature Extractor Network (OFENet). Our networks (XiNet) are trained to solve stochastic optimization problems over the RL networks' weights and the parameters of variational Bernoulli distributions for 0/1 Random Variables $\xi$ scaling each unit in the networks. The stochastic problem formulation induces regularization terms that promote convergence of the variational parameters to 0 when a unit contributes little to the performance. In this case, the corresponding structure is rendered permanently inactive and pruned from its network. We propose a cost-aware, sparsity-promoting regularization scheme, tailored to the DenseNet architecture of OFENets expressing the parameter complexity of involved networks in terms of the parameters of the RVs in these networks. Then, when matching this cost with the regularization terms, the many hyperparameters associated with them are automatically selected, effectively combining the RL objectives and network compression. We evaluate our method on continuous control benchmarks (MuJoCo) and the Soft Actor-Critic RL agent, demonstrating that OFENets can be pruned considerably with minimal loss in performance. Furthermore, our results confirm that pruning large networks during training produces more efficient and higher performing RL agents rather than training smaller networks from scratch.

Related papers

• Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning [57.3885832382455]
  We show that introducing static network sparsity alone can unlock further scaling potential beyond dense counterparts with state-of-the-art architectures.<n>Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity.
  arXiv  Detail & Related papers  (2025-06-20T17:54:24Z)
• Interpretable Reinforcement Learning for Load Balancing using Kolmogorov-Arnold Networks [6.373998211961586]
  Reinforcement learning (RL) has been increasingly applied to network control problems, such as load balancing.<n>Existing RL approaches often suffer from lack of interpretability and difficulty in extracting controller equations.<n>We propose the use of Kolmogorov-Arnold Networks (KAN) for interpretable RL in network control.
  arXiv  Detail & Related papers  (2025-05-20T14:56:31Z)
• Efficient Training of Deep Neural Operator Networks via Randomized Sampling [0.0]
  We introduce a random sampling technique to be adopted the training of DeepONet.<n>We demonstrate substantial reductions in training time while achieving comparable or lower overall test errors relative to the traditional training approach.<n>Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet.
  arXiv  Detail & Related papers  (2024-09-20T07:18:31Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks [63.24965775030673]
  We propose a novel Reinforcement Learning (RL) approach to design generic Congestion Control (CC) algorithms. Our solution, MARLIN, uses the Soft Actor-Critic algorithm to maximize both entropy and return. We trained MARLIN on a real network with varying background traffic patterns to overcome the sim-to-real mismatch.
  arXiv  Detail & Related papers  (2023-02-02T18:27:20Z)
• Single-Shot Pruning for Offline Reinforcement Learning [47.886329599997474]
  Deep Reinforcement Learning (RL) is a powerful framework for solving complex real-world problems. One way to tackle this problem is to prune neural networks leaving only the necessary parameters. We close the gap between RL and single-shot pruning techniques and present a general pruning approach to the Offline RL.
  arXiv  Detail & Related papers  (2021-12-31T18:10:02Z)
• On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement [0.8459686722437155]
  We compare two Deep Reinforcement Learning algorithms: a pure DRL-based algorithm and a hybrid DRL as a hybrid DRL-heuristic algorithm. The evaluation results show that the proposed hybrid DRL-heuristic approach is more robust and reliable in case of unpredictable network load changes than pure DRL.
  arXiv  Detail & Related papers  (2021-08-05T10:24:33Z)
• Continual Learning in Recurrent Neural Networks [67.05499844830231]
  We evaluate the effectiveness of continual learning methods for processing sequential data with recurrent neural networks (RNNs) We shed light on the particularities that arise when applying weight-importance methods, such as elastic weight consolidation, to RNNs. We show that the performance of weight-importance methods is not directly affected by the length of the processed sequences, but rather by high working memory requirements.
  arXiv  Detail & Related papers  (2020-06-22T10:05:12Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

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.