Fast Task-Adaptation for Tasks Labeled Using Natural Language in Reinforcement Learning

2019-10-09 · Matthias Hutsebaut-Buysse, Kevin Mets, Steven Latré

Over its lifetime, a reinforcement learning agent is often tasked with different tasks. How to efficiently adapt a previously learned control policy from one task to another, remains an open research question. In this paper, we investigate how instructions formulated in natural language can enable faster and more effective task adaptation. This can serve as the basis for developing language instructed skills, which can be used in a lifelong learning setting. Our method is capable of assessing, given a set of developed base control policies, which policy will adapt best to a new unseen task.

📄 PDF Abstract BibTeX arXiv:1910.04040

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization

2015-10-15 · Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang

This paper addresses classification tasks on a particular target domain in which labeled training data are only available from source domains different from (but related to) the target. Two closely related frameworks, do…

Domain Adaptation Domain Generalization General Classification Object Recognition+1

Neural Unsupervised Domain Adaptation in NLP---A Survey

2020-05-31 · COLING 2020 8 · Alan Ramponi, Barbara Plank

Deep neural networks excel at learning from labeled data and achieve state-of-the-art resultson a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift,…

Domain Adaptation Out-of-Distribution Generalization Survey Unsupervised Domain Adaptation

Investigation on Data Adaptation Techniques for Neural Named Entity Recognition

2021-10-12 · ACL 2021 5 · Evgeniia Tokarchuk, David Thulke, Weiyue Wang, Christian Dugast 외

Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional …

Data Augmentation named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)

Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation

2020-03-05 · CVPR 2020 6 · Min-Hung Chen, Baopu Li, Yingze Bao, Ghassan AlRegib 외

Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory. One main challenge is the problem of spatiotemporal variations (e.g. different people may p…

Action Segmentation Domain Adaptation

Labeled Memory Networks for Online Model Adaptation

2017-07-05 · Shiv Shankar, Sunita Sarawagi

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks…

Few-Shot Learning Meta-Learning model