# Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.24305 · HTML: https://mlsanity.com/paper/2509.24305/

## Key facts

- Cited by 1 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 38 of its 55 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## 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 38)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [Lower Bounds for Non-Convex Stochastic Optimization](https://mlsanity.com/paper/1912.02365/) (2019)
- [Momentum-Based Variance Reduction in Non-Convex SGD](https://mlsanity.com/paper/1905.10018/) (2019)
- [Top-K Off-Policy Correction for a REINFORCE Recommender System](https://mlsanity.com/paper/1812.02353/) (2018)
- [Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes](https://mlsanity.com/paper/2102.00135/) (2021)
- [Revisiting Distributed Synchronous SGD](https://mlsanity.com/paper/1702.05800/) (2017)
- [Momentum Improves Normalized SGD](https://mlsanity.com/paper/2002.03305/) (2020)
- [Lower Bounds for Finding Stationary Points I](https://mlsanity.com/paper/1710.11606/) (2017)
- [Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies](https://mlsanity.com/paper/1906.08383/) (2019)
- [Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization](https://mlsanity.com/paper/1506.08272/) (2015)
- [Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning](https://mlsanity.com/paper/2206.08307/) (2022)
- [A general sample complexity analysis of vanilla policy gradient](https://mlsanity.com/paper/2107.11433/) (2021)
- [Federated Reinforcement Learning with Environment Heterogeneity](https://mlsanity.com/paper/2204.02634/) (2022)
- [Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays](https://mlsanity.com/paper/2206.07638/) (2022)
- [Lower Bounds for Finding Stationary Points II: First-Order Methods](https://mlsanity.com/paper/1711.00841/) (2017)
- [Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies](https://mlsanity.com/paper/2302.01734/) (2023)
- [Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies](https://mlsanity.com/paper/2210.01400/) (2022)
- [Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations](https://mlsanity.com/paper/2006.13476/) (2020)
- [An Asynchronous Mini-Batch Algorithm for Regularized Stochastic Optimization](https://mlsanity.com/paper/1505.04824/) (2015)
- [Asynchronous Stochastic Optimization Robust to Arbitrary Delays](https://mlsanity.com/paper/2106.11879/) (2021)
- [Momentum-Based Policy Gradient Methods](https://mlsanity.com/paper/2007.06680/) (2020)
- [On the Global Optimum Convergence of Momentum-based Policy Gradient](https://mlsanity.com/paper/2110.10116/) (2021)
- [Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model](https://mlsanity.com/paper/2305.12387/) (2023)

## Built on by (most cited first, 1 of 1)

- [Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis](https://mlsanity.com/paper/2610.01896/) (2026)

## Abstract (arXiv)

We study distributed reinforcement learning (RL) with policy gradient methods under asynchronous and parallel computations and communications. While non-distributed methods are well understood theoretically and have achieved remarkable empirical success, their distributed counterparts remain less explored, particularly in the presence of heterogeneous asynchronous computations and communication bottlenecks. We introduce two new algorithms, Rennala NIGT and Malenia NIGT, which implement asynchronous policy gradient aggregation and achieve state-of-the-art efficiency. In the homogeneous setting, Rennala NIGT provably improves the total computational and communication complexity while supporting the AllReduce operation. In the heterogeneous setting, Malenia NIGT simultaneously handles asynchronous computations and heterogeneous environments with strictly better theoretical guarantees. Our results are further corroborated by experiments, showing that our methods significantly outperform prior approaches.