An Integrated Approach To Neural Architecture Search For Deep Q-networks

Abstract

The performance of deep reinforcement learning agents is fundamentally constrained by their neural network architecture, a choice traditionally made through expensive hyperparameter searches and then fixed throughout training. This work investigates whether online, adaptive architecture optimization can escape this constraint and outperform static designs. We introduce NAS-DQN, an agent that integrates a learned neural architecture search controller directly into the DRL training loop, enabling dynamic network reconfiguration based on cumulative performance feedback. We evaluate NAS-DQN against three fixed-architecture baselines and a random search control on a continuous control task, conducting experiments over multiple random seeds. Our results demonstrate that NAS-DQN achieves superior final performance, sample efficiency, and policy stability while incurring negligible computational overhead. Critically, the learned search strategy substantially outperforms both undirected random

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrahmani2025an

Related papers

• Optimizing The Neural Architecture Of Reinforcement Learning Agents (2020)0.00
• Differentiable Architecture Search For Reinforcement Learning (2021)0.00
• Deep Q-networks For Accelerating The Training Of Deep Neural Networks (2016)0.00
• Adaptive \(q\)-network: On-the-fly Target Selection For Deep Reinforcement Learning (2024)0.00
• Neural Architecture Evolution In Deep Reinforcement Learning For Continuous Control (2019)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00
• Ardns-fn-quantum: A Quantum-enhanced Reinforcement Learning Framework With Cognitive-inspired Adaptive Exploration For Dynamic Environments (2025)2.26
• NROWAN-DQN: A Stable Noisy Network With Noise Reduction And Online Weight Adjustment For Exploration (2020)0.00