相关论文: Structure Detection for Contextual Reinforcement L…

Multi-domain text classification (MDTC) aims to leverage all available resources from multiple domains to learn a predictive model that can generalize well on these domains. Recently, many MDTC methods adopt adversarial learning,…

Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time. To avoid time-discretization approximation of the…

In-context learning (ICL), the remarkable ability to solve a task from only input exemplars, is often assumed to be a unique hallmark of Transformer models. By examining commonly employed synthetic ICL tasks, we demonstrate that multi-layer…

Models with transparent inner structure and high classification performance are required to reduce potential risk and provide trust for users in domains like health care, finance, security, etc. However, existing models are hard to…

Autonomous vehicles have shown promising potential to be a groundbreaking technology for improving the safety of road users. For these vehicles, as well as many other safety-critical robotic technologies, to be deployed in real-world…

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific…

We consider problems in sequential decision making with natural multi-level structure, where sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure has remained a…

Motivated by the recent discovery of a statistical and computational reduction from contextual bandits to offline regression (Simchi-Levi and Xu, 2021), we address the general (stochastic) Contextual Markov Decision Process (CMDP) problem…

Interpretability of AI models allows for user safety checks to build trust in such AIs. In particular, Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for…

Despite rapid progress in AI agents for enterprise automation and decision-making, their real-world deployment and further performance gains remain constrained by limited data quality and quantity, complex real-world reasoning demands,…

Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integration of complex…

Segmentation-based methods are widely used for scene text detection due to their superiority in describing arbitrary-shaped text instances. However, two major problems still exist: 1) current label generation techniques are mostly empirical…

This paper addresses the problem of learning control policies for mobile robots, modeled as unknown Markov Decision Processes (MDPs), that are tasked with temporal logic missions, such as sequencing, coverage, or surveillance. The MDP…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Hierarchical Reinforcement Learning (HRL) enhances the scalability of decision-making in long-horizon tasks by introducing temporal abstraction through options-policies that span multiple timesteps. Despite its theoretical appeal, the…

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL…

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…

Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks.…

Multi-task reinforcement learning (MTRL) aims to endow a single agent with the ability to perform well on multiple tasks. Recent works have focused on developing novel sophisticated architectures to improve performance, often resulting in…

Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop interactions largely…