Reinforcement learning (RL) has attracted much attention recently, as new and emerging AI-
based applications are demanding the capabilities to intelligently react to environment …

Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular
computation patterns, each of which typically exhibits opportunities for distributed …

Reinforcement learning (RL) algorithms involve the deep nesting of distinct components,
where each component typically exhibits opportunities for distributed computation. Current …

Deep reinforcement learning (RL) has led to many recent and groundbreaking advances.
However, these advances have often come at the cost of both increased scale in the …

Training machine learning models in parallel is an increasingly important workload. We
accelerate distributed parallel training by designing a communication primitive that uses a …

As the scale of distributed training increases, it brings huge communication overhead in
clusters. Some works try to reduce the communication cost through gradient compression or …

We propose a novel framework for efficient parallelization of deep reinforcement learning
algorithms, enabling these algorithms to learn from multiple actors on a single machine. The …

Abstract Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibitively
large number of training samples for learning complex tasks. Many recent works on …

There has been significant progress in developing reinforcement learning (RL) training
systems. Past works such as IMPALA, Apex, Seed RL, Sample Factory, and others, aim to …

We present a modern scalable reinforcement learning agent called SEED (Scalable,
Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only …