# InDRiVE: Reward-Free World-Model Pretraining for Autonomous Driving via Latent Disagreement

arXiv: https://arxiv.org/abs/2512.18850 · HTML: https://mlsanity.com/paper/2512.18850/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)
- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

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

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Dream to Drive with Predictive Individual World Model](https://mlsanity.com/paper/2501.16733/) (2025)
- [Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies](https://mlsanity.com/paper/2411.10171/) (2024)

## Built on by (most cited first, 1 of 1)

- [Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA](https://mlsanity.com/paper/2604.27994/) (2026)

## Abstract (arXiv)

Model-based reinforcement learning (MBRL) can reduce interaction cost for autonomous driving by learning a predictive world model, but it typically still depends on task-specific rewards that are difficult to design and often brittle under distribution shift. This paper presents InDRiVE, a DreamerV3-style MBRL agent that performs reward-free pretraining in CARLA using only intrinsic motivation derived from latent ensemble disagreement. Disagreement acts as a proxy for epistemic uncertainty and drives the agent toward under-explored driving situations, while an imagination-based actor-critic learns a planner-free exploration policy directly from the learned world model. After intrinsic pretraining, we evaluate zero-shot transfer by freezing all parameters and deploying the pretrained exploration policy in unseen towns and routes. We then study few-shot adaptation by training a task policy with limited extrinsic feedback for downstream objectives (lane following and collision avoidance). Experiments in CARLA across towns, routes, and traffic densities show that disagreement-based pretraining yields stronger zero-shot robustness and robust few-shot collision avoidance under town shift and matched interaction budgets, supporting the use of intrinsic disagreement as a practical reward-free pretraining signal for reusable driving world models.