Addressing stale gradients in asynchronous federated deep reinforcement learning

Stanley, Justin

Addressing stale gradients in asynchronous federated deep reinforcement learning

File

Stanley_iastate_0097M_21011.pdf (2.73 MB)

Date

2023-08

Authors

Stanley, Justin

Advisor

Jannesari, Ali

Quinn, Christopher

Tian, Jin

Huai, Mengdi

Altmetrics

Department

Computer Science

Abstract

Advancements in reinforcement learning (RL) via deep neural networks have enabled their application to a variety of real-world problems. However, these applications often suffer from long training times. While attempts to distribute training have been successful in controlled scenarios, they face challenges in heterogeneous-capacity, unstable, and privacy critical environments. This work applies concepts from federated learning (FL) to distributed RL, specifically addressing the stale gradient problem. A deterministic framework for asynchronous federated RL is utilized to explore dynamic methods for handling stale gradient updates in the Arcade Learning Environment. Experimental results from applying these methods to two Atari-2600 games demonstrate a relative speedup of up to 95\% compared to plain A3C in large and unstable federations.