mlsanityData to 14 Oct 2026

Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping

arXiv 2507.16249 ↗First posted 22 Jul 2025cs.LG cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Mapping deep neural networks (DNNs) to hardware is critical for optimizing latency, energy consumption, and resource utilization, making it a cornerstone of high-performance accelerator design. Due to the vast and complex mapping space, reinforcement learning (RL) has emerged as a promising approach-but its effectiveness is often limited by sample inefficiency. We present a decentralized multi-agent reinforcement learning (MARL) framework designed to overcome this challenge. By distributing the search across multiple agents, our framework accelerates exploration. To avoid inefficiencies from training multiple agents in parallel, we introduce an agent clustering algorithm that assigns similar mapping parameters to the same agents based on correlation analysis. This enables a decentralized, parallelized learning process that significantly improves sample efficiency. Experimental results show our MARL approach improves sample efficiency by 30-300x over standard single-agent RL, achieving up to 32.61x latency reduction and 16.45x energy-delay product (EDP) reduction under iso-sample conditions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

11 of 25 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  6. 2016OpenAI Gymcited by 1,736
  7. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
  8. 2016Maximizing CNN Accelerator Efficiency Through Resource Partitioningcited by 29
  9. 2021Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Searchcited by 24
  10. 2019Optimally Scheduling CNN Convolutions for Efficient Memory Accesscited by 10
  11. 2023ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Designcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective
  2. 2024MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search
  3. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  4. 2024MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning
  5. 2024Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance
  6. 2026Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning
  7. 2025Multi-agent In-context Coordination via Decentralized Memory Retrieval
  8. 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning