相关论文: Mapping representations in Reinforcement Learning …

We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…

In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The main idea is to…

The many-to-many multilingual neural machine translation can translate between language pairs unseen during training, i.e., zero-shot translation. Improving zero-shot translation requires the model to learn universal representations and…

We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor…

Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applications. Zero-shot learning models rely on learning an…

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their…

A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centric RL paradigm…

Recent advancements in NLP have resulted in models with specialized strengths, such as processing multimodal inputs or excelling in specific domains. However, real-world tasks, like multimodal translation, often require a combination of…

Zero-shot learning (ZSL) aims to learn models that can recognize unseen image semantics based on the training of data with seen semantics. Recent studies either leverage the global image features or mine discriminative local patch features…

This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, generalisation of formally specified instructions. In particular,…

Unsupervised zero-shot reinforcement learning (RL) has emerged as a powerful paradigm for pretraining behavioral foundation models (BFMs), enabling agents to solve a wide range of downstream tasks specified via reward functions in a…

We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we…

Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space…

Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…

Zero-shot reinforcement learning (RL) promises to provide agents that can perform any task in an environment after an offline, reward-free pre-training phase. Methods leveraging successor measures and successor features have shown strong…

Methods of deep machine learning enable to to reuse low-level representations efficiently for generating more abstract high-level representations. Originally, deep learning has been applied passively (e.g., for classification purposes).…

We present a new embedding-based framework for zero-shot learning (ZSL). Most embedding-based methods aim to learn the correspondence between an image classifier (visual representation) and its class prototype (semantic representation) for…

We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network…