paper-with-me

Papers

Learning Massively Multitask World Models for Continuous Control

2025-11-24 · Nicklas Hansen, Hao Su, Xiaolong Wang arxiv

General-purpose control demands agents that act across many tasks and embodiments, yet research on reinforcement learning (RL) for continuous control remains dominated by single-task or offline regimes, reinforcing a view that online RL does not scale. Inspired by the foundation model recipe (large-scale pretraining followed by light RL) we ask whether a single agent can be trained on hundreds of tasks with online interaction. To accelerate research in this direction, we introduce a new benchmark with 200 diverse tasks spanning many domains and embodiments, each with language instructions, demonstrations, and optionally image observations. We then present \emph{Newt}, a language-conditioned multitask world model that is first pretrained on demonstrations to acquire task-aware representations and action priors, and then jointly optimized with online interaction across all tasks. Experiments show that Newt yields better multitask performance and data-efficiency than a set of strong baselines, exhibits strong open-loop control, and enables rapid adaptation to unseen tasks. We release our environments, demonstrations, code for training and evaluation, as well as 200+ checkpoints.

📄 PDF Abstract BibTeX arXiv:2511.19584

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningContinuous Control

Similar Papers 제목 키워드 기반

Massively Multitask Networks for Drug Discovery

2015-02-06 · Bharath Ramsundar, Steven Kearnes, Patrick Riley, Dale Webster 외

Massively multitask neural architectures provide a learning framework for drug discovery that synthesizes information from many distinct biological sources. To train these architectures at scale, we gather large amounts …

Drug Discovery

M3TQA: Massively Multilingual Multitask Table Question Answering

2025-08-22 · Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu 외 arxiv

Tabular data is a fundamental component of real-world information systems, yet most research in table understanding remains confined to English, leaving multilingual comprehension significantly underexplored. Existing mu…

Question Answering

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

2024-02-09 · Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma 외

We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offl…

Computational Efficiencycontinuous-controlContinuous ControlContrastive Learning+5

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

2026-06-04 · Johan Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon 외 arxiv

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, mak…

Representation LearningReinforcement LearningContinuous Control

Multitask Adaptation by Retrospective Exploration with Learned World Models

2021-10-25 · Artem Zholus, Aleksandr I. Panov

Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner. However, no information is reused between the tasks. In this work, we propose a meta-learned addressing model called RA…

Model-based Reinforcement Learning