相关论文: Gradient Surgery for Multi-Task Learning

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

The key to success in machine learning (ML) is the use of effective data representations. Traditionally, data representations were hand-crafted. Recently it has been demonstrated that, given sufficient data, deep neural networks can learn…

Deep reinforcement learning has made significant strides in various robotic tasks. However, employing deep reinforcement learning methods to tackle multi-stage tasks still a challenge. Reinforcement learning algorithms often encounter…

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Many healthcare decisions involve navigating through a multitude of treatment options in a sequential and iterative manner to find an optimal treatment pathway with the goal of an optimal patient outcome. Such optimization problems may be…

The current deep learning model is of a single-grade, that is, it learns a deep neural network by solving a single nonconvex optimization problem. When the layer number of the neural network is large, it is computationally challenging to…

Recently, researchers have utilized neural networks to accurately solve partial differential equations (PDEs), enabling the mesh-free method for scientific computation. Unfortunately, the network performance drops when encountering a high…

Segmentation of multiple surfaces in medical images is a challenging problem, further complicated by the frequent presence of weak boundary and mutual influence between adjacent objects. The traditional graph-based optimal surface…

Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space. However, despite…

Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…

Tree-based models are widely recognized for their interpretability and have proven effective in various application domains, particularly in high-stakes domains. However, learning decision trees (DTs) poses a significant challenge due to…

This paper addresses a critical societal consideration in the application of Reinforcement Learning (RL): ensuring equitable outcomes across different demographic groups in multi-task settings. While previous work has explored fairness in…

In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…

To train deep learning models faster, distributed training on multiple GPUs is the very popular scheme in recent years. However, the communication bandwidth is still a major bottleneck of training performance. To improve overall training…

Self-supervised learning (SSL) has achieved remarkable performance in various medical imaging tasks by dint of priors from massive unlabelled data. However, regarding a specific downstream task, there is still a lack of an instruction book…

Machine Unlearning has recently garnered significant attention, aiming to selectively remove knowledge associated with specific data while preserving the model's performance on the remaining data. A fundamental challenge in this process is…

In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as "single-tasking multiple tasks". The network thus…

Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specifically in the case of meta-reinforcement learning (meta-RL),…

Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields, including pattern recognition, robotics, recommendation-systems, and gaming. Similarly, graph neural networks (GNN) have also demonstrated their…

Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robotic problems with a…