Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

actor-critic network

An actor-critic network is a reinforcement learning architecture that combines policy-based and value-based methods through two cooperating neural network components. In this framework, the actor network determines and executes actions according to the current state of the environment, while the critic network evaluates those actions by estimating the corresponding value function or expected return. Feedback from the critic, often measured as an advantage or temporal difference error, directs the actor to adjust its policy parameters to favor higher-performing actions while the critic iteratively refines its value estimates. This cooperative structure reduces the learning variance typically found in pure policy gradient methods, stabilizes training dynamics, and allows the model to effectively handle complex continuous or discrete control tasks.

1 item

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Sixing Yu, Arya Mazaheri, Ali Jannesari

OrganizationsIowa State UniversityTechnische Universität Darmstadt

Why you should read this

Proposes a multi-stage graph embedding framework that captures hierarchical neural network topologies to automatically learn optimal, FLOP-constrained pruning policies via reinforcement learning across diverse architectures.

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters’ local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach with state-of-the-art model compression methods. We evaluated our method on various models from typical to mobile-friendly networks, such as ResNet family, VGG-16, MobileNet-v1/v2, and ShuffleNet. Results show that our method can achieve higher compression ratios with a minimal fine-tuning cost yet yields outstanding and competitive performance. The code is open-sourced at https://github.com/yusx-swapp/GNN-RL-Model-Compression.

Added

2026-10-03