相关论文: Goal-Aware Cross-Entropy for Multi-Target Reinforc…

Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially…

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

In this work we employ multitask learning to capitalize on the structure that exists in related supervised tasks to train complex neural networks. It allows training a network for multiple objectives in parallel, in order to improve…

Cross-entropy (CE) is the default training loss for supervised classification, but its sample efficiency is limited when labels are scarce. Existing remedies primarily act on the data side, via augmentation, synthesis, or transfer from…

Deploying multiple robots for target search and tracking has many practical applications, yet the challenge of planning over unknown or partially known targets remains difficult to address. With recent advances in deep learning, intelligent…

Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learning simply sums up…

What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks? When the desired (test time) goal distribution is too distant to offer a useful learning signal, we argue that the agent should not…

In this work we present a new method of black-box optimization and constraint satisfaction. Existing algorithms that have attempted to solve this problem are unable to consider multiple modes, and are not able to adapt to changes in…

Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design,…

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…

Both goal-agnostic and goal-oriented tasks have practical value for robotic grasping: goal-agnostic tasks target all objects in the workspace, while goal-oriented tasks aim at grasping pre-assigned goal objects. However, most current…

In multi-robot collaborative area search, a key challenge is to dynamically balance the two objectives of exploring unknown areas and covering specific targets to be rescued. Existing methods are often constrained by homogeneous graph…

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…

Training effective embodied AI agents often involves manual reward engineering, expert imitation, specialized components such as maps, or leveraging additional sensors for depth and localization. Another approach is to use neural…

Gaze target detection aims at determining the image location where a person is looking. While existing studies have made significant progress in this area by regressing accurate gaze heatmaps, these achievements have largely relied on…

The utilization of broad datasets has proven to be crucial for generalization for a wide range of fields. However, how to effectively make use of diverse multi-task data for novel downstream tasks still remains a grand challenge in…

This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The…

In robotics, it is essential to be able to plan efficiently in high-dimensional continuous state-action spaces for long horizons. For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is…

Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…

Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. Promising results have been achieved via Mean Teacher, however, pseudo labeling which is the…