# DreamerV3-XP: Optimizing exploration through uncertainty estimation

arXiv: https://arxiv.org/abs/2510.21418 · HTML: https://mlsanity.com/paper/2510.21418/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Curious Replay for Model-based Adaptation](https://mlsanity.com/paper/2306.15934/) (2023)

## Built on by (most cited first, 2 of 2)

- [Reading the Room: Implicit Confusion Encoding in Recurrent World Model States](https://mlsanity.com/paper/2608.21582/) (2026)
- [EpicWorldModel: Exploration-driven Planning with Latent World Models](https://mlsanity.com/paper/2610.05996/) (2026)

## Abstract (arXiv)

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.