Related papers: Enhancing Policy Learning with World-Action Model

Learning cooperative multi-agent policies directly from high-dimensional, multimodal sensory inputs like pixels and audio (from pixels) is notoriously sample-inefficient. Model-free Multi-Agent Reinforcement Learning (MARL) algorithms…

We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, addressing the critical limitations of prior unified world…

Pretrained video generation models provide strong priors for robot control, but existing unified world action models still struggle to decode reliable actions without substantial robot-specific training. We attribute this limitation to a…

Behavior cloning methods for robot learning suffer from poor generalization due to limited data support beyond expert demonstrations. Recent approaches leveraging video prediction models have shown promising results by learning rich…

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However,…

Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…

Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision-Language-Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots. Recent work…

A World Model is a compressed spatial and temporal representation of a real world environment that allows one to train an agent or execute planning methods. However, world models are typically trained on observations from the real world…

Pre-training large models on vast amounts of web data has proven to be an effective approach for obtaining powerful, general models in domains such as language and vision. However, this paradigm has not yet taken hold in reinforcement…

Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm adopts a two-stage approach that trains latent action model…

Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world environments. Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world…

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

Embodied action planning is a core challenge in robotics, requiring models to generate precise actions from visual observations and language instructions. While video generation world models are promising, their reliance on pixel-level…

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting…

Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evidence of how the physical world changes. Latent action models offer a promising way to…

We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion…

Differentiable simulators represent an environment's dynamics as a differentiable function. Within robotics and autonomous driving, this property is used in Analytic Policy Gradients (APG), which relies on backpropagating through the…

In sequential decision-making environments, the primary approaches for training agents are Reinforcement Learning (RL) and Imitation Learning (IL). Unlike RL, which relies on modeling a reward function, IL leverages expert demonstrations,…

Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number…