A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 11 Jun 2021.
Builds on
21 of 32 references.
References · 21
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
- 2017A Brief Survey of Deep Reinforcement Learningcited by 483
- 2015Policy Distillationcited by 440
- 2018SNAS: Stochastic Neural Architecture Searchcited by 289
- 2020MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulationcited by 57
- 2019Hardware/Software Co-Exploration of Neural Architecturescited by 50
- 2020AutoGAN-Distiller: Searching to Compress Generative Adversarial Networkscited by 50
- 2019FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edgecited by 48
9 more
- 2019Control Regularization for Reduced Variance Reinforcement Learningcited by 37
- 2020EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutionscited by 36
- 2020Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Acceleratorcited by 30
- 2016Maximizing CNN Accelerator Efficiency Through Resource Partitioningcited by 29
- 2020AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICscited by 26
- 2020DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architecturescited by 16
- 2020SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computationcited by 16
- 2020TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domaincited by 12
- 2020DNA: Differentiable Network-Accelerator Co-Searchcited by 11
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1.
3 papers.