English
Related papers

Related papers: ResWM: Residual-Action World Model for Visual RL

200 papers

Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforcement learning (RL). However, many existing methods do not directly generate actions alongside states…

Machine Learning · Computer Science 2026-05-14 Zongyue Li , Xiao Han , Yusong Li , Niklas Strauss , Matthias Schubert

Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Given pre-segmented videos, the task is to recognize actions…

Computer Vision and Pattern Recognition · Computer Science 2017-06-28 Ahsan Iqbal , Alexander Richard , Hilde Kuehne , Juergen Gall

Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have shown prior success, but lack robust geometric information that…

Robotics · Computer Science 2025-09-18 Guanxing Lu , Baoxiong Jia , Puhao Li , Yixin Chen , Ziwei Wang , Yansong Tang , Siyuan Huang

We present the Multi-Agent Transformer World Model (MATWM), a novel transformer-based world model designed for multi-agent reinforcement learning in both vector- and image-based environments. MATWM combines a decentralized imagination…

Machine Learning · Computer Science 2025-06-24 Azad Deihim , Eduardo Alonso , Dimitra Apostolopoulou

Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of…

While recent model-free Reinforcement Learning (RL) methods have demonstrated human-level effectiveness in gaming environments, their success in everyday tasks like visual navigation has been limited, particularly under significant…

Machine Learning · Computer Science 2024-04-04 Rudra P. K. Poudel , Harit Pandya , Stephan Liwicki , Roberto Cipolla

Object-centric world models (OCWM) aim to decompose visual scenes into object-level representations, providing structured abstractions that could improve compositional generalization and data efficiency in reinforcement learning. We…

Artificial Intelligence · Computer Science 2025-11-12 Stefano Ferraro , Akihiro Nakano , Masahiro Suzuki , Yutaka Matsuo

To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinforcement learning (RL) has emerged as a promising approach by…

Robotics · Computer Science 2024-07-29 Dechen Gao , Shuangyu Cai , Hanchu Zhou , Hang Wang , Iman Soltani , Junshan Zhang

In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. While previous approaches leveraging discrete latent spaces,…

Machine Learning · Computer Science 2025-03-04 Aidan Scannell , Mohammadreza Nakhaei , Kalle Kujanpää , Yi Zhao , Kevin Sebastian Luck , Arno Solin , Joni Pajarinen

World models enable robots to conduct counterfactual reasoning in physical environments by predicting future world states. While conventional approaches often prioritize pixel-level reconstruction of future scenes, such detailed rendering…

Robotics · Computer Science 2025-12-22 Zhiwei Zhang , Hui Zhang , Kaihong Huang , Chenghao Shi , Huimin Lu

World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Execute" approach, which uses video prediction to infer actions…

Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and adapt to environment dynamics, highlighting the need for…

Computation and Language · Computer Science 2026-02-10 Xiao Yu , Baolin Peng , Ruize Xu , Yelong Shen , Pengcheng He , Suman Nath , Nikhil Singh , Jiangfeng Gao , Zhou Yu

Imagination in world models is crucial for enabling agents to learn long-horizon policy in a sample-efficient manner. Existing recurrent state-space model (RSSM)-based world models depend on single-step statistical inference to capture the…

Machine Learning · Computer Science 2025-10-24 Lingyi Wang , Rashed Shelim , Walid Saad , Naren Ramakrishnan

In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, {\Delta}t, and training over a diverse range of {\Delta}t values --…

Machine Learning · Computer Science 2025-06-11 Anh N. Nhu , Sanghyun Son , Ming Lin

Robotic manipulation requires sophisticated commonsense reasoning, a capability naturally possessed by large-scale Vision-Language Models (VLMs). While VLMs show promise as zero-shot planners, their lack of grounded physical understanding…

Robotics · Computer Science 2026-03-18 Emily Yue-Ting Jia , Weiduo Yuan , Tianheng Shi , Vitor Guizilini , Jiageng Mao , Yue Wang

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Machine Learning · Computer Science 2023-10-25 Yunhai Feng , Nicklas Hansen , Ziyan Xiong , Chandramouli Rajagopalan , Xiaolong Wang

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient robot learning from visual observations. Yet the current approaches typically train a single model end-to-end for learning both visual…

Robotics · Computer Science 2023-05-30 Younggyo Seo , Danijar Hafner , Hao Liu , Fangchen Liu , Stephen James , Kimin Lee , Pieter Abbeel

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Qi Wang , Zhipeng Zhang , Baao Xie , Xin Jin , Yunbo Wang , Shiyu Wang , Liaomo Zheng , Xiaokang Yang , Wenjun Zeng

Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning…

Robotics · Computer Science 2026-04-28 Junjin Xiao , Yandan Yang , Xinyuan Chang , Ronghan Chen , Feng Xiong , Mu Xu , Wei-Shi Zheng , Qing Zhang

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined…

Artificial Intelligence · Computer Science 2026-05-21 Yucen Wang , Rui Yu , Fengming Zhang , Junjie Lu , Xinyao Qin , Tianxiang Zhang , Kaixin Wang , Li Zhao