paper-with-me

홈 › Papers

Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

2017-06-15 · ICML 2017 8 · Junhyuk Oh, Satinder Singh, Honglak Lee, Pushmeet Kohli

As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning useful skills that solve subtasks. In this problem, we consider two types of generalizations: to previously unseen instructions and to longer sequences of instructions. For generalization over unseen instructions, we propose a new objective which encourages learning correspondences between similar subtasks by making analogies. For generalization over sequential instructions, we present a hierarchical architecture where a meta controller learns to use the acquired skills for executing the instructions. To deal with delayed reward, we propose a new neural architecture in the meta controller that learns when to update the subtask, which makes learning more efficient. Experimental results on a stochastic 3D domain show that the proposed ideas are crucial for generalization to longer instructions as well as unseen instructions.

📄 PDF Abstract BibTeX arXiv:1706.05064

Code (1)

seriousssam/zero-shot-task-generalization-implementation pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Zero-Shot Generalization during Instruction Tuning: Insights from Similarity and Granularity

2024-06-17 · Bingxiang He, Ning Ding, Cheng Qian, Jia Deng 외

Understanding alignment techniques begins with comprehending zero-shot generalization brought by instruction tuning, but little of the mechanism has been understood. Existing work has largely been confined to the task le…

Continual LearningZero-shot Generalization

ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization

2022-01-18 · Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao 외

We propose a multitask pretraining approach ZeroPrompt for zero-shot generalization, focusing on task scaling and zero-shot prompting. While previous models are trained on only a few dozen tasks, we scale to 1,000 tasks …

Zero-shot GeneralizationZero-Shot Learning

Multitask Prompted Training Enables Zero-Shot Task Generalization

2021-10-15 · ICLR 2022 4 · Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach 외

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learn…

BenchmarkingDecoderLanguage ModellingPrompt Engineering+1

A Generalization Theory for Zero-Shot Prediction

2025-07-12 · Ronak Mehta, Zaid Harchaoui arxiv

A modern paradigm for generalization in machine learning and AI consists of pre-training a task-agnostic foundation model, generally obtained using self-supervised and multimodal contrastive learning. The resulting repre…

Contrastive Learning

GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions

2023-05-24 · Woojeong Jin, Subhabrata Mukherjee, Yu Cheng, Yelong Shen 외

Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks. However, such generalization to vision-language tasks including grounding and ge…

ObjectQuestion AnsweringVisual Commonsense ReasoningVisual Question Answering