A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning
arXiv:2106.06577
Abstract
Driven by the explosive interest in applying deep reinforcement learning (DRL) agents to numerous real-time control and decision-making applications, there has been a growing demand to deploy DRL agents to empower daily-life intelligent devices, while the prohibitive complexity of DRL stands at odds with limited on-device resources. In this work, we propose an Automated Agent Accelerator Co-Search (A3C-S) framework, which to our best knowledge is the first to automatically co-search the optimally matched DRL agents and accelerators that maximize both test scores and hardware efficiency. Extensive experiments consistently validate the superiority of our A3C-S over state-of-the-art techniques.
Accepted at DAC 2021. arXiv admin note: text overlap with arXiv:2012.13091
References in corpus (6)
- A Brief Survey of Deep Reinforcement Learning
- Categorical Reparameterization with Gumbel-Softmax
- DARTS: Differentiable Architecture Search
- AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
- Control Regularization for Reduced Variance Reinforcement Learning
- DNA: Differentiable Network-Accelerator Co-Search