# Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning

arXiv: https://arxiv.org/abs/2005.06105 · HTML: https://mlsanity.com/paper/2005.06105/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2020.

## Built on by (most cited first, 10 of 10)

- [Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning](https://mlsanity.com/paper/2102.12920/) (2021)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT](https://mlsanity.com/paper/2202.03575/) (2022)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration](https://mlsanity.com/paper/2205.01423/) (2022)
- [The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication](https://mlsanity.com/paper/2103.13026/) (2021)
- [Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning](https://mlsanity.com/paper/2201.12718/) (2022)
- [Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning](https://mlsanity.com/paper/2309.06097/) (2023)
- [Enhancing Deep Deterministic Policy Gradients on Continuous Control Tasks with Decoupled Prioritized Experience Replay](https://mlsanity.com/paper/2512.05320/) (2025)
- [FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation](https://mlsanity.com/paper/2603.28455/) (2026)

## Abstract (arXiv)

Traditional distributed deep reinforcement learning (RL) commonly relies on exchanging the experience replay memory (RM) of each agent. Since the RM contains all state observations and action policy history, it may incur huge communication overhead while violating the privacy of each agent. Alternatively, this article presents a communication-efficient and privacy-preserving distributed RL framework, coined federated reinforcement distillation (FRD). In FRD, each agent exchanges its proxy experience replay memory (ProxRM), in which policies are locally averaged with respect to proxy states clustering actual states. To provide FRD design insights, we present ablation studies on the impact of ProxRM structures, neural network architectures, and communication intervals. Furthermore, we propose an improved version of FRD, coined mixup augmented FRD (MixFRD), in which ProxRM is interpolated using the mixup data augmentation algorithm. Simulations in a Cartpole environment validate the effectiveness of MixFRD in reducing the variance of mission completion time and communication cost, compared to the benchmark schemes, vanilla FRD, federated reinforcement learning (FRL), and policy distillation (PD).