Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics

ArXi:2602.12643v2 Announce Type: replace-cross We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By embedding state-action pairs into a latent space in which the true value function is approximately linear, our method s a single set of hyperparameters across diverse domains -- from continuous control with low-dimensional and pixel inputs to high-dimensional Atari games.