Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics

TL;DR

This paper presents a neural network-based world model framework for robotics that enables robust, scalable policy optimization by accurately capturing complex dynamics and facilitating sim-to-real transfer.

Contribution

It introduces a novel dual-autoregressive, self-supervised world model framework that improves long-horizon predictions and adaptability across diverse robotic tasks.

Findings

Enhanced long-horizon prediction accuracy

Improved sim-to-real transfer capabilities

Robust policy optimization in complex environments

Abstract

Learning robust and generalizable world models is crucial for enabling efficient and scalable robotic control in real-world environments. In this work, we introduce a novel framework for learning world models that accurately capture complex, partially observable, and stochastic dynamics. The proposed method employs a dual-autoregressive mechanism and self-supervised training to achieve reliable long-horizon predictions without relying on domain-specific inductive biases, ensuring adaptability across diverse robotic tasks. We further propose a policy optimization framework that leverages world models for efficient training in imagined environments and seamless deployment in real-world systems. This work advances model-based reinforcement learning by addressing the challenges of long-horizon prediction, error accumulation, and sim-to-real transfer. By providing a scalable and robust framework, the introduced methods pave the way for adaptive and efficient robotic systems in real-world applications.