Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912496491692032 |
|---|---|
| author | Krishnan, Srivatsan Jabbour, Jason Zhang, Dan Jaques, Natasha Faust, Aleksandra Omidshafiei, Shayegan Reddi, Vijay Janapa |
| author_facet | Krishnan, Srivatsan Jabbour, Jason Zhang, Dan Jaques, Natasha Faust, Aleksandra Omidshafiei, Shayegan Reddi, Vijay Janapa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16249 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping Krishnan, Srivatsan Jabbour, Jason Zhang, Dan Jaques, Natasha Faust, Aleksandra Omidshafiei, Shayegan Reddi, Vijay Janapa Machine Learning Multiagent Systems 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. |
| title | Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping |
| topic | Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2507.16249 |