DreamerV3-XP: Optimizing exploration through uncertainty estimation
Machine Learning
2025-10-27 v1 Artificial Intelligence
Abstract
We introduce DreamerV3-XP, an extension of DreamerV3 that improves exploration and learning efficiency. This includes (i) a prioritized replay buffer, scoring trajectories by return, reconstruction loss, and value error and (ii) an intrinsic reward based on disagreement over predicted environment rewards from an ensemble of world models. DreamerV3-XP is evaluated on a subset of Atari100k and DeepMind Control Visual Benchmark tasks, confirming the original DreamerV3 results and showing that our extensions lead to faster learning and lower dynamics model loss, particularly in sparse-reward settings.
Keywords
Cite
@article{arxiv.2510.21418,
title = {DreamerV3-XP: Optimizing exploration through uncertainty estimation},
author = {Lukas Bierling and Davide Pasero and Jan-Henrik Bertrand and Kiki Van Gerwen},
journal= {arXiv preprint arXiv:2510.21418},
year = {2025}
}