World Models as Reference Trajectories for Rapid Motor Adaptation

📅 2025-05-21
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the abrupt degradation of control performance caused by sudden system dynamics changes, this paper proposes a reflective world model (RWM) dual-control framework. RWM directly utilizes the deterministic world model’s predictive output as an implicit, dynamically adaptive reference trajectory, thereby decoupling long-horizon reward optimization from millisecond-level latent-space motion execution. It introduces, for the first time, a synergistic dual-control architecture integrating latent-space model predictive control, online latent-action correction, and hierarchical reinforcement learning. Evaluated on high-dimensional continuous control tasks, RWM achieves second-scale dynamics adaptation, reduces computational overhead by 87%, and maintains policy performance above 98% of the optimal—significantly outperforming existing model-based baselines.

Technology Category

Application Category

📝 Abstract
Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a dual control framework that uses world model predictions as implicit reference trajectories for rapid adaptation. Our method separates the control problem into long-term reward maximization through reinforcement learning and robust motor execution through rapid latent control. This dual architecture achieves significantly faster adaptation with low online computational cost compared to model-based RL baselines, while maintaining near-optimal performance. The approach combines the benefits of flexible policy learning through reinforcement learning with rapid error correction capabilities, providing a principled approach to maintaining performance in high-dimensional continuous control tasks under varying dynamics.
Problem

Research questions and friction points this paper is trying to address.

Deploying learned policies in changing real-world dynamics
Separating control into long-term rewards and rapid adaptation
Maintaining performance in high-dimensional continuous control tasks
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses reflexive world models for rapid adaptation
Separates long-term reward and robust execution
Combines policy learning with error correction
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
C
Carlos Stein Brito
NightCity Labs, Champalimaud Centre for the Unknown, Lisbon, Portugal
D
Daniel McNamee
Champalimaud Centre for the Unknown, Lisbon, Portugal