相关论文: Zero-Shot Reinforcement Learning via Function Enco…

We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a \emph{target task}. We propose a…

Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a hurdle for its practical application on real robots. To address this issue, safe reinforcement…

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges,…

Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies,…

Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained…

Zero-shot classification is a generalization task where no instance from the target classes is seen during training. To allow for test-time transfer, each class is annotated with semantic information, commonly in the form of attributes or…

Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a…

Zero-shot learning (ZSL) tackles the novel class recognition problem by transferring semantic knowledge from seen classes to unseen ones. Existing attention-based models have struggled to learn inferior region features in a single image by…

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their goals differ.…

This paper studies the problem of autonomous exploration under localization uncertainty for a mobile robot with 3D range sensing. We present a framework for self-learning a high-performance exploration policy in a single simulation…

Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on…

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the…

Humans inherently possess generalizable visual representations that empower them to efficiently explore and interact with the environments in manipulation tasks. We advocate that such a representation automatically arises from…

In the field of reinforcement learning (RL), agents are often tasked with solving a variety of problems differing only in their reward functions. In order to quickly obtain solutions to unseen problems with new reward functions, a popular…

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to unseen ones so that the latter can be recognised without any training samples. This is made possible by learning a projection function between a feature space and a…

For the task with complicated manipulation in unstructured environments, traditional hand-coded methods are ineffective, while reinforcement learning can provide more general and useful policy. Although the reinforcement learning is able to…

The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy…

Effective feature selection, representation and transformation are principal steps in machine learning to improve prediction accuracy, model generalization and computational efficiency. Reinforcement learning provides a new perspective…

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality.…