# Scaling Curriculum Learning For Autonomous Driving

arXiv: https://arxiv.org/abs/2608.22549 · HTML: https://mlsanity.com/paper/2608.22549/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- 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, 30 of 33)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research](https://mlsanity.com/paper/2310.08710/) (2023)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments](https://mlsanity.com/paper/1910.07224/) (2019)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [The Waymo Open Sim Agents Challenge](https://mlsanity.com/paper/2305.12032/) (2023)
- [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023)
- [Robust Autonomy Emerges from Self-Play](https://mlsanity.com/paper/2502.03349/) (2025)
- [ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling](https://mlsanity.com/paper/2306.12241/) (2023)
- [Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world](https://mlsanity.com/paper/2206.09889/) (2022)
- [CAT: Closed-loop Adversarial Training for Safe End-to-End Driving](https://mlsanity.com/paper/2310.12432/) (2023)
- [GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS](https://mlsanity.com/paper/2408.01584/) (2024)
- [Learning to Act by Predicting the Future](https://mlsanity.com/paper/1611.01779/) (2016)
- [Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft](https://mlsanity.com/paper/2106.14876/) (2021)
- [No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery](https://mlsanity.com/paper/2408.15099/) (2024)
- [Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments](https://mlsanity.com/paper/2503.22496/) (2025)
- [Building reliable sim driving agents by scaling self-play](https://mlsanity.com/paper/2502.14706/) (2025)
- [Proximal Curriculum for Reinforcement Learning Agents](https://mlsanity.com/paper/2304.12877/) (2023)
- [Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design](https://mlsanity.com/paper/2310.02782/) (2023)
- [minimax: Efficient Baselines for Autocurricula in JAX](https://mlsanity.com/paper/2311.12716/) (2023)
- [Continual Driving Policy Optimization with Closed-Loop Individualized Curricula](https://mlsanity.com/paper/2309.14209/) (2023)

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

- [CounterPlay: Counterfactual Post-Training for Self-Play Driving Policies](https://mlsanity.com/paper/2609.21617/) (2026)

## Abstract (arXiv)

Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic scenarios and billions of interactions within a matter of days. Although such high-throughput feeds RL algorithms faster than ever, their sample-efficiency has not kept pace: As the standard training scheme, domain randomization uniformly samples scenarios, thereby consuming a vast number of interactions on cases that contribute little to learning. Curriculum learning offers a remedy by adaptively prioritizing scenarios that matter most to policy improvement. We present CL4AD, the first integration of curriculum learning into batched autonomous driving simulators by framing scenario selection as an unsupervised environment design problem. We introduce utility functions that shape curricula based on success rates and the realism of the agent's behavior, in addition to existing regret-estimation functions. Large-scale experiments in GPUDRIVE demonstrate that curriculum learning achieves a 99% success rate a billion steps earlier than domain randomization, reducing wall-clock time by 77%, and outperforms heuristic curricula with static and dynamic attributes, with only one exception at the largest scale. An ablation under limited compute shows that curriculum learning improves sample efficiency by 67%. We also investigate how utility functions behave at scale, and how prioritized scenarios evolve during training. We release an implementation of CLForAD in GPUDRIVE.