English
Related papers

Related papers: Enhancing Policy Learning with World-Action Model

200 papers

Action-conditioned world models (ACWMs) have shown strong promise for video prediction and decision-making. However, existing benchmarks are largely restricted to egocentric navigation or narrow, task-specific robotics datasets, offering…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Haotian Xue , Yipu Chen , Liqian Ma , Zelin Zhao , Lama Moukheiber , Yuchen Zhu , Yongxin Chen

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Nilaksh , Saurav Jha , Artem Zholus , Sarath Chandar

Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Amir Bar , Gaoyue Zhou , Danny Tran , Trevor Darrell , Yann LeCun

The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping…

Robotics · Computer Science 2026-04-29 Yi Chen , Yuying Ge , Hui Zhou , Mingyu Ding , Yixiao Ge , Xihui Liu

Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. Traditional methods heavily rely on representation learning that is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Sanghwan Kim , Daoji Huang , Yongqin Xian , Otmar Hilliges , Luc Van Gool , Xi Wang

Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. Some SSIL methods learn an inverse dynamics model (IDM) to…

Machine Learning · Computer Science 2026-02-04 Sacha Morin , Moonsub Byeon , Alexia Jolicoeur-Martineau , Sébastien Lachapelle

World Action Models (WAMs) are an emerging family of policies that tie robot action generation to future-observation modeling. In this work, we focus on the joint video--action modeling paradigm, where actions and imagined future…

Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…

Robotics · Computer Science 2022-10-20 Chenning Yu , Hongzhan Yu , Sicun Gao

While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving friction and restitution.…

Machine Learning · Computer Science 2025-05-06 Wenxuan Li , Hang Zhao , Zhiyuan Yu , Yu Du , Qin Zou , Ruizhen Hu , Kai Xu

Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios. One approach to these problems is to…

Artificial Intelligence · Computer Science 2026-02-05 Feiyu Zhu , Jean Oh , Reid Simmons

Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely observing and imitating others. This ability highly depends on…

Machine Learning · Computer Science 2023-12-05 Xingyuan Zhang , Philip Becker-Ehmck , Patrick van der Smagt , Maximilian Karl

A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken…

Artificial Intelligence · Computer Science 2026-01-23 Zhikang Chen , Tingting Zhu

Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, existing approaches struggle to strike a balance between…

World models have recently attracted growing interest in Multi-Agent Reinforcement Learning (MARL) due to their ability to improve sample efficiency for policy learning. However, accurately modeling environments in MARL is challenging due…

Multiagent Systems · Computer Science 2025-10-27 Yang Zhang , Xinran Li , Jianing Ye , Shuang Qiu , Delin Qu , Xiu Li , Chongjie Zhang , Chenjia Bai

We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and…

Robotics · Computer Science 2025-12-23 Ilia Larchenko , Gleb Zarin , Akash Karnatak

Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Most reinforcement…

Artificial Intelligence · Computer Science 2023-01-18 Jonathan Balloch , Zhiyu Lin , Robert Wright , Xiangyu Peng , Mustafa Hussain , Aarun Srinivas , Julia Kim , Mark O. Riedl

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

Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current frames and actions, which can then be used for planning. However, the objective…

Machine Learning · Computer Science 2025-10-23 Jacob Berg , Chuning Zhu , Yanda Bao , Ishan Durugkar , Abhishek Gupta

Policy learning focuses on devising strategies for agents in embodied artificial intelligence systems to perform optimal actions based on their perceived states. One of the key challenges in policy learning involves handling complex,…

Robotics · Computer Science 2025-07-08 Hao Huang , Shuaihang Yuan , Geeta Chandra Raju Bethala , Congcong Wen , Anthony Tzes , Yi Fang

A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to…

Artificial Intelligence · Computer Science 2016-12-02 Shehroze Bhatti , Alban Desmaison , Ondrej Miksik , Nantas Nardelli , N. Siddharth , Philip H. S. Torr