Learning Latent Dynamic Robust Representations for World Models

1 code implementation • 10 May 2024 • Ruixiang Sun, Hongyu Zang, Xin Li, Riashat Islam

Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's knowledge about the underlying dynamics of the environment, enabling learning a world model as a useful planner.

Model-based Reinforcement Learning