Optimizing The Neural Architecture Of Reinforcement Learning Agents

Abstract

Reinforcement learning (RL) enjoyed significant progress over the last years. One of the most important steps forward was the wide application of neural networks. However, architectures of these neural networks are typically constructed manually. In this work, we study recently proposed neural architecture search (NAS) methods for optimizing the architecture of RL agents. We carry out experiments on the Atari benchmark and conclude that modern NAS methods find architectures of RL agents outperforming a manually selected one.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymazyavkina2020optimizing

Related papers

• An Integrated Approach To Neural Architecture Search For Deep Q-networks (2025)0.00
• Differentiable Architecture Search For Reinforcement Learning (2021)0.00
• Importance Of Using Appropriate Baselines For Evaluation Of Data-efficiency In Deep Reinforcement Learning For Atari (2020)0.00
• Reinforcement Learning And Its Connections With Neuroscience And Psychology (2020)12.25
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• Neuroevolution Of Recurrent Architectures On Control Tasks (2023)4.52
• Adapting The Function Approximation Architecture In Online Reinforcement Learning (2021)0.00