Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing
Summary: Nitro leverages serverless functions to spawn ephemeral actors for instant high-concurrency sampling, avoiding serverful startup and scalability bottlenecks. Using a metric-driven, cost-aware actor-scaling heuristic, Nitro yields up to 6× higher final rewards and 42% lower training cost. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Hanfei Yu (Stevens Institute of Technology)
- 2. Jacob Carter (Louisiana State University)
- 3. Hao Wang (Stevens Institute of Technology)
- 4. Devesh Tiwari (Northeastern University)
- 5. Jian Li (State University of New York at Stony Brook)
- 6. Seung-Jong Park (Missouri University of Science and Technology)
BibTeX Citation
@article{yu_vldb25,
title = {{Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing}},
author = {Yu, Hanfei and Carter, Jacob and Wang, Hao and Tiwari, Devesh and Li, Jian and Park, Seung-Jong},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {1},
pages = {66--79},
doi = {10.14778/3696435.3696441},
url = {https://doi.org/10.14778/3696435.3696441},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,169 | Towards Demystifying Serverless Machine Learning Training | 2021 | SIGMOD | 7.6715222e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,067 | Distributed Deep Learning on Data Systems: A Comparative Analysis of Approaches | 2021 | VLDB |
| 2 | 2,162 | Heterogeneity-aware Distributed Parameter Servers | 2017 | SIGMOD |
| 3 | 521 | PyTorch Distributed: Experiences on Accelerating Data Parallel Training | 2020 | VLDB |
| 4 | 9,546 | NeutronTP: Load-Balanced Distributed Full-Graph GNN Training with Tensor Parallelism | 2025 | VLDB |
| 5 | 10,596 | NeutronCloud: Resource-Aware Distributed GNN Training in Fluctuating Cloud Environments | 2026 | VLDB |
| 6 | 9,000 | Optimizing Inference Serving on Serverless Platforms | 2022 | VLDB |
| 7 | 7,114 | Serverless Data Science - Are We There Yet? A Case Study of Model Serving | 2022 | SIGMOD |
| 8 | 4,987 | Releasing Cloud Databases from the Chains of Performance Prediction Models | 2017 | CIDR |
| 9 | 3,169 | Towards Demystifying Serverless Machine Learning Training | 2021 | SIGMOD |
| 10 | 7,194 | Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning | 2018 | VLDB |