# InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model

arXiv: https://arxiv.org/abs/2503.05573 · HTML: https://mlsanity.com/paper/2503.05573/

## Key facts

- Cited by 2 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 19 of its 26 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-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, 19 of 19)

- [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)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)
- [Self-Supervised Exploration via Disagreement](https://mlsanity.com/paper/1906.04161/) (2019)
- [Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models](https://mlsanity.com/paper/1507.00814/) (2015)
- [Model-Based Imitation Learning for Urban Driving](https://mlsanity.com/paper/2210.07729/) (2022)
- [End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances](https://mlsanity.com/paper/1911.10868/) (2019)
- [RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments](https://mlsanity.com/paper/2002.12292/) (2020)
- [Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)](https://mlsanity.com/paper/2402.16720/) (2024)
- [An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey](https://mlsanity.com/paper/2209.08890/) (2022)
- [Dream to Drive with Predictive Individual World Model](https://mlsanity.com/paper/2501.16733/) (2025)

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

- [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026)
- [Driving Beyond Privilege: Distilling Dense-Reward Knowledge into Sparse-Reward Policies](https://mlsanity.com/paper/2512.04279/) (2025)

## Abstract (arXiv)

Model-based Reinforcement Learning (MBRL) has emerged as a promising paradigm for autonomous driving, where data efficiency and robustness are critical. Yet, existing solutions often rely on carefully crafted, task specific extrinsic rewards, limiting generalization to new tasks or environments. In this paper, we propose InDRiVE (Intrinsic Disagreement based Reinforcement for Vehicle Exploration), a method that leverages purely intrinsic, disagreement based rewards within a Dreamer based MBRL framework. By training an ensemble of world models, the agent actively explores high uncertainty regions of environments without any task specific feedback. This approach yields a task agnostic latent representation, allowing for rapid zero shot or few shot fine tuning on downstream driving tasks such as lane following and collision avoidance. Experimental results in both seen and unseen environments demonstrate that InDRiVE achieves higher success rates and fewer infractions compared to DreamerV2 and DreamerV3 baselines despite using significantly fewer training steps. Our findings highlight the effectiveness of purely intrinsic exploration for learning robust vehicle control behaviors, paving the way for more scalable and adaptable autonomous driving systems.