# QForce-RL: Quantized FPGA-Optimized Reinforcement Learning Compute Engine

arXiv: https://arxiv.org/abs/2506.07046 · HTML: https://mlsanity.com/paper/2506.07046/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 7 of 7)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [ChipNeMo: Domain-Adapted LLMs for Chip Design](https://mlsanity.com/paper/2311.00176/) (2023)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [Chip Placement with Deep Reinforcement Learning](https://mlsanity.com/paper/2004.10746/) (2020)
- [QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning](https://mlsanity.com/paper/1910.01055/) (2019)
- [Flex-PE: Flexible and SIMD Multi-Precision Processing Element for AI Workloads](https://mlsanity.com/paper/2412.11702/) (2024)
- [ShortcutFusion: From Tensorflow to FPGA-based accelerator with reuse-aware memory allocation for shortcut data](https://mlsanity.com/paper/2106.08167/) (2021)

## Built on by (most cited first, 2 of 2)

- [Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2510.10676/) (2025)
- [BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment](https://mlsanity.com/paper/2604.24273/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) has outperformed other counterparts in sequential decision-making and dynamic environment control. However, FPGA deployment is significantly resource-expensive, as associated with large number of computations in training agents with high-quality images and possess new challenges. In this work, we propose QForce-RL takes benefits of quantization to enhance throughput and reduce energy footprint with light-weight RL architecture, without significant performance degradation. QForce-RL takes advantages from E2HRL to reduce overall RL actions to learn desired policy and QuaRL for quantization based SIMD for hardware acceleration. We have also provided detailed analysis for different RL environments, with emphasis on model size, parameters, and accelerated compute ops. The architecture is scalable for resource-constrained devices and provide parametrized efficient deployment with flexibility in latency, throughput, power, and energy efficiency. The proposed QForce-RL provides performance enhancement up to 2.3x and better FPS - 2.6x compared to SoTA works.