Learning Massively Multitask World Models for Continuous Control

• URL: http://arxiv.org/abs/2511.19584v2
• Date: Tue, 02 Dec 2025 01:48:49 GMT
• Title: Learning Massively Multitask World Models for Continuous Control
• Authors: Nicklas Hansen, Hao Su, Xiaolong Wang,
• Abstract summary: General-purpose control demands agents that act across many tasks and embodiments.<n>We ask whether a single agent can be trained on hundreds of tasks with online interaction.<n>We present emphNewt, a language-conditioned multitask world model that is first pretrained on demonstrations.
• Score: 25.87102585211245
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners [60.75160178669076]
  We show that the use of high-capacity value models trained via cross-entropy and conditioned on learnable task embeddings addresses the problem of task interference in online reinforcement learning.<n>We test our approach on 7 multi-task benchmarks with over 280 unique tasks, spanning high degree-of-freedom humanoid control and discrete vision-based RL.
  arXiv  Detail & Related papers  (2025-05-29T06:41:45Z)
• Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations [24.041217922654738]
  Continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks.<n>Online RL methods can automatically explore the state space to solve each new task.<n>However, discovering sequences of actions that lead to a non-zero reward becomes exponentially more difficult as the task horizon increases.<n>We introduce a systematic reward-shaping framework that distills the information contained in 1) a task-agnostic prior data set and 2) a small number of task-specific expert demonstrations.
  arXiv  Detail & Related papers  (2024-12-02T04:37:12Z)
• Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning [62.3886343725955]
  We introduce a novel value-based reinforcement learning algorithm that learns a critic network that outputs Q-values over a sequence of actions.<n>Experiments show that CQN-AS outperforms several baselines on a variety of sparse-reward humanoid control and tabletop manipulation tasks.
  arXiv  Detail & Related papers  (2024-11-19T01:23:52Z)
• Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal [54.93261535899478]
  In real-world applications, such as robotic control of reinforcement learning, the tasks are changing, and new tasks arise in a sequential order.<n>This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge.<n>We propose a rehearsal-based continual diffusion model, called Continual diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability)
  arXiv  Detail & Related papers  (2024-09-04T08:21:47Z)
• Offline Multitask Representation Learning for Reinforcement Learning [86.26066704016056]
  We study offline multitask representation learning in reinforcement learning (RL) We propose a new algorithm called MORL for offline multitask representation learning. Our theoretical results demonstrate the benefits of using the learned representation from the upstream offline task instead of directly learning the representation of the low-rank model.
  arXiv  Detail & Related papers  (2024-03-18T08:50:30Z)
• Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss [61.355272240758]
  Premier-TACO is a multitask feature representation learning approach. It is designed to improve few-shot policy learning efficiency in sequential decision-making tasks.
  arXiv  Detail & Related papers  (2024-02-09T05:04:40Z)
• Learning to Modulate pre-trained Models in RL [22.812215561012874]
  Fine-tuning a pre-trained model often suffers from catastrophic forgetting. Our study shows that with most fine-tuning approaches, the performance on pre-training tasks deteriorates significantly. We propose a novel method, Learning-to-Modulate (L2M), that avoids the degradation of learned skills by modulating the information flow of the frozen pre-trained model.
  arXiv  Detail & Related papers  (2023-06-26T17:53:05Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)
• Provable Benefit of Multitask Representation Learning in Reinforcement Learning [46.11628795660159]
  This paper theoretically characterizes the benefit of representation learning under the low-rank Markov decision process (MDP) model. To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask reinforcement learning.
  arXiv  Detail & Related papers  (2022-06-13T04:29:02Z)
• Towards More Generalizable One-shot Visual Imitation Learning [81.09074706236858]
  A general-purpose robot should be able to master a wide range of tasks and quickly learn a novel one by leveraging past experiences. One-shot imitation learning (OSIL) approaches this goal by training an agent with (pairs of) expert demonstrations. We push for a higher level of generalization ability by investigating a more ambitious multi-task setup.
  arXiv  Detail & Related papers  (2021-10-26T05:49:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.