# SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems

arXiv: https://arxiv.org/abs/2405.03967 · HTML: https://mlsanity.com/paper/2405.03967/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 57 of its 149 references that are in the map.
- First posted on arXiv 7 May 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 30 of 57)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems](https://mlsanity.com/paper/2203.01387/) (2022)
- [A Review of Safe Reinforcement Learning: Methods, Theory and Applications](https://mlsanity.com/paper/2205.10330/) (2022)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Acme: A Research Framework for Distributed Reinforcement Learning](https://mlsanity.com/paper/2006.00979/) (2020)
- [SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving](https://mlsanity.com/paper/2010.09776/) (2020)
- [Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction](https://mlsanity.com/paper/2006.03041/) (2020)
- [Federated Reinforcement Learning: Techniques, Applications, and Open Challenges](https://mlsanity.com/paper/2108.11887/) (2021)
- [Generative Adversarial User Model for Reinforcement Learning Based Recommendation System](https://mlsanity.com/paper/1812.10613/) (2018)
- [Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning](https://mlsanity.com/paper/1911.04175/) (2019)
- [DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning](https://mlsanity.com/paper/2102.11492/) (2021)
- [Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare](https://mlsanity.com/paper/2305.01738/) (2023)
- [Accelerated Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1803.02811/) (2018)
- [The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond](https://mlsanity.com/paper/2305.10697/) (2023)
- [Efficient Parallel Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1705.04862/) (2017)
- [A Modern Primer on Processing in Memory](https://mlsanity.com/paper/2012.03112/) (2020)
- [CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1809.05188/) (2018)
- [Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks](https://mlsanity.com/paper/2109.14320/) (2021)

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

- [LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM](https://mlsanity.com/paper/2604.04523/) (2026)
- [UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture](https://mlsanity.com/paper/2410.23805/) (2024)

## Abstract (arXiv)

Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To overcome this, SwiftRL explores Processing-In-Memory (PIM) architectures to accelerate RL workloads. We achieve near-linear performance scaling by implementing RL algorithms like Tabular Q-learning and SARSA on UPMEM PIM systems and optimizing for hardware. Our experiments on OpenAI GYM environments using UPMEM hardware demonstrate superior performance compared to CPU and GPU implementations.