A3C-S: Automated Agent Accelerator Co-search Towards Efficient Deep Reinforcement Learning

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfu2021a3c

Related papers

• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Human-inspired Framework To Accelerate Reinforcement Learning (2023)0.00
• Using Monte Carlo Tree Search As A Demonstrator Within Asynchronous Deep RL (2018)0.00
• SEED RL: Scalable And Efficient Deep-rl With Accelerated Central Inference (2019)0.00
• Efficient Reinforcement Learning Development With Rlzoo (2020)3.58
• A Further Exploration Of Deep Multi-agent Reinforcement Learning With Hybrid Action Space (2022)5.84
• Dynamic Sparse Training For Deep Reinforcement Learning (2021)0.00