AI RESEARCH
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
arXiv CS.LG
•
ArXi:2603.07083v1 Announce Type: new Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract representations for effective planning and control. Existing approaches typically employ reconstruction-based objectives in the observation space, which can render representations sensitive to task-irrelevant details. Recent alternatives trade reconstruction for auxiliary action prediction heads or view augmentation strategies, but perform worse in the Crafter environment than reconstruction-based methods.