# Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition

arXiv: https://arxiv.org/abs/2610.11662 · HTML: https://mlsanity.com/paper/2610.11662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 30 of 33)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets](https://mlsanity.com/paper/2108.09640/) (2021)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [The ApolloScape Open Dataset for Autonomous Driving and its Application](https://mlsanity.com/paper/1803.06184/) (2018)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention](https://mlsanity.com/paper/1703.10631/) (2017)
- [TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios](https://mlsanity.com/paper/2210.06609/) (2022)
- [A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective](https://mlsanity.com/paper/2202.02215/) (2022)
- [Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving](https://mlsanity.com/paper/2403.04133/) (2024)
- [World Models for Autonomous Driving: An Initial Survey](https://mlsanity.com/paper/2403.02622/) (2024)
- [CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving](https://mlsanity.com/paper/2408.10845/) (2024)
- [On Offline Evaluation of Vision-based Driving Models](https://mlsanity.com/paper/1809.04843/) (2018)
- ["Curse of rarity" for autonomous vehicles](https://mlsanity.com/paper/2207.02749/) (2022)
- [CAT: Closed-loop Adversarial Training for Safe End-to-End Driving](https://mlsanity.com/paper/2310.12432/) (2023)
- [Scenarios for Development, Test and Validation of Automated Vehicles](https://mlsanity.com/paper/1801.08598/) (2018)
- [LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2501.15850/) (2025)
- [State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections](https://mlsanity.com/paper/2207.04361/) (2022)
- [doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigation](https://mlsanity.com/paper/2412.05893/) (2024)
- [CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models](https://mlsanity.com/paper/2502.15119/) (2025)
- [Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control](https://mlsanity.com/paper/2505.15304/) (2025)
- [DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving](https://mlsanity.com/paper/2408.16647/) (2024)

## Abstract (arXiv)

Autonomous driving capabilities depend strongly on the distribution of scenarios encountered during training. Existing methods commonly construct or dynamically adapt training scenario distributions using surrogate criteria such as realism, difficulty, or risk. However, these predefined surrogates may misrepresent training value, leading to inefficient use of training resources. To address this limitation, we propose a Lamarckian evolutionary framework that replaces surrogate-based guidance with competition among candidate distributions. We formulate training strategy discovery as a multi-stage bilevel optimization problem and use Lamarckian evolution algorithm to approximate its solution. At the outer level, Darwinian crossover, mutation, and selection explore the scenario distribution space; at the inner level, policy learning acquires new capabilities, and Lamarckian inheritance transfers them to subsequent stages, allowing scenario distributions and policy capabilities to co-evolve. The resulting evolutionary trajectories reveal recurring stage-wise regularities among high-value distributions, characterized by capability accumulation through stage-wise challenge rotation. We further distill these regularities into a lightweight, reusable Lamarckian Training Strategy. Experiments show that, compared with the baseline, the complete framework reduces performance loss by up to 25.07%, while the lightweight strategy still achieves a 19.13% reduction. These results demonstrate that evolutionary competition can both discover effective training strategies and reveal reusable stage-wise patterns in how the value of training distributions changes with policy capability. Code is available on GitHub.