Related papers: Spreeze: High-Throughput Parallel Reinforcement Le…

Efficient data transfers over high-speed, long-distance shared networks require proper utilization of available network bandwidth. Using parallel TCP streams enables an application to utilize network parallelism and can improve transfer…

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains…

Reinforcement Learning (RL) has achieved significant success in application domains such as robotics, games and health care. However, training RL agents is very time consuming. Current implementations exhibit poor performance due to…

Parallel Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources, allowing for faster generation of samples, estimation of values, and policy improvement. These computational…

Deep Reinforcement Learning (DRL) is vital in various AI applications. DRL algorithms comprise diverse compute kernels, which may not be simultaneously optimized using a homogeneous architecture. However, even with available heterogeneous…

Deep Reinforcement Learning (DRL) has emerged as a promising approach for handling highly dynamic and nonlinear Active Flow Control (AFC) problems. However, the computational cost associated with training DRL models presents a significant…

As large language models (LLMs) continue to scale and new GPUs are released even more frequently, there is an increasing demand for LLM post-training in heterogeneous environments to fully leverage underutilized mid-range or…

LLM post-training with reinforcement learning (RL) requires frequent synchronization of large model parameters between the trainer and distributed rollout actors. High-throughput RL post-training therefore relies on dedicated RDMA HPC…

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL…

Reinforcement learning (RL) is a paradigm increasingly used to align large language models. Popular RL algorithms utilize multiple workers and can be modeled as a graph, where each node is the status of a worker and each edge represents…

Reinforcement learning (RL) trains many agents, which is resource-intensive and must scale to large GPU clusters. Different RL training algorithms offer different opportunities for distributing and parallelising the computation. Yet,…

Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS)…

In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since…

Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a simulation of the environment. In particular, there are key…

Recent advances in parallel computing and GPU acceleration have created new opportunities for computation-intensive learning problems such as Active SLAM -- where actions are selected to reduce uncertainty and improve joint mapping and…

As the demands for superior agents grow, the training complexity of Deep Reinforcement Learning (DRL) becomes higher. Thus, accelerating training of DRL has become a major research focus. Dividing the DRL training process into subtasks and…

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…

We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems. Our method combines three novel components: (1) a work donation algorithm, (2) a…

Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to…

The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward…