相关论文: Theoretical Study of Conflict-Avoidant Multi-Objec…

Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple…

An intelligent decision-making system enabled by Vehicle-to-Everything (V2X) communications is essential to achieve safe and efficient autonomous driving (AD), where two types of decisions have to be made at different timescales, i.e.,…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Reinforcement Learning (RL) robot controllers usually aggregate many task objectives into one scalar reward. While large-scale proximal policy optimisation (PPO) has enabled impressive results such as robust robot locomotion in the real…

Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action…

Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent problems are often harder to train and analyze…

Many sequential decision-making problems need optimization of different objectives which possibly conflict with each other. The conventional way to deal with a multi-task problem is to establish a scalar objective function based on a linear…

The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling,…

In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a…

Multi-task learning (MTL) has been widely adopted for its ability to simultaneously learn multiple tasks. While existing gradient manipulation methods often yield more balanced solutions than simple scalarization-based approaches, they…

The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling,…

The time allocation problem in multi-function cognitive radar systems focuses on the trade-off between scanning for newly emerging targets and tracking the previously detected targets. We formulate this as a multi-objective optimization…

Adapting models pre-trained on large-scale datasets is a proven way to reach strong performance quickly for down-stream tasks. However, the growth of state-of-the-art mod-els makes traditional full fine-tuning unsuitable and difficult,…

Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well on a new domain. In this paper, we take a step towards…

Multi-task learning (MTL) models have demonstrated impressive results in computer vision, natural language processing, and recommender systems. Even though many approaches have been proposed, how well these approaches balance different…

Deep reinforcement learning (DRL) algorithms have successfully been demonstrated on a range of challenging decision making and control tasks. One dominant component of recent deep reinforcement learning algorithms is the target network…

In recent years, Multi-task Learning (MTL) has yielded immense success in Recommender System (RS) applications. However, current MTL-based recommendation models tend to disregard the session-wise patterns of user-item interactions because…

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as the standard paradigm for improving reasoning capability of large language models, while Multi-Token Prediction (MTP) has been a widely adopted module in pretraining.…

The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a…

Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing methods use an adaptive weight updating scheme, where task…