Related papers: Highly Parallelized Reinforcement Learning Trainin…

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…

Machine scheduling aims to optimize job assignments to machines while adhering to manufacturing rules and job specifications. This optimization leads to reduced operational costs, improved customer demand fulfillment, and enhanced…

Cooperative communication is an effective approach to improve spectrum utilization. In order to reduce outage probability of communication system, most studies propose various schemes for relay selection and power allocation, which are…

Deep reinforcement learning has demonstrated remarkable success across various domains. However, the tight coupling between training and inference processes makes accelerating DRL training an essential challenge for DRL optimization. Two…

The Dynamic Task Assignment Problem (DTAP) concerns matching resources to tasks in real time while minimizing some objectives, like resource costs or task cycle time. In this work, we consider a DTAP variant where every task is a case…

Deep neural networks (DNNs) exploit many layers and a large number of parameters to achieve excellent performance. The training process of DNN models generally handles large-scale input data with many sparse features, which incurs high…

Network slicing is a critical driver for guaranteeing the diverse service level agreements (SLA) in 5G and future networks. Recently, deep reinforcement learning (DRL) has been widely utilized for resource allocation in network slicing.…

Interference among concurrent transmissions in a wireless network is a key factor limiting the system performance. One way to alleviate this problem is to manage the radio resources in order to maximize either the average or the worst-case…

The rapid advancements in machine learning techniques have led to significant achievements in various real-world robotic tasks. These tasks heavily rely on fast and energy-efficient inference of deep neural network (DNN) models when…

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

The quantum cloud computing paradigm presents unique challenges in task placement due to the dynamic and heterogeneous nature of quantum computation resources. Traditional heuristic approaches fall short in adapting to the rapidly evolving…

Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable…

This article proposes a model-based deep reinforcement learning (DRL) method to design emergency control strategies for short-term voltage stability problems in power systems. Recent advances show promising results in model-free DRL-based…

Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with…

While researchers in the asset management industry have mostly focused on techniques based on financial and risk planning techniques like Markowitz efficient frontier, minimum variance, maximum diversification or equal risk parity, in…

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…

Closed-loop control remains an open challenge in soft robotics. The nonlinear responses of soft actuators under dynamic loading conditions limit the use of analytic models for soft robot control. Traditional methods of controlling soft…

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization…

With the increasing popularity of robotics in industrial control and autonomous driving, deep reinforcement learning (DRL) raises the attention of various fields. However, DRL computation on the modern powerful GPU platform is still…

Intelligent wireless networks have long been expected to have self-configuration and self-optimization capabilities to adapt to various environments and demands. In this paper, we develop a novel distributed hierarchical deep reinforcement…