# CaRL: Learning Scalable Planning Policies with Simple Rewards

arXiv: https://arxiv.org/abs/2504.17838 · HTML: https://mlsanity.com/paper/2504.17838/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods.
- Builds on 69 of its 99 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Placed in

- 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 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [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)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [End-to-End Urban Driving by Imitating a Reinforcement Learning Coach](https://mlsanity.com/paper/2108.08265/) (2021)
- [Understanding plasticity in neural networks](https://mlsanity.com/paper/2303.01486/) (2023)
- [Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving](https://mlsanity.com/paper/2305.06242/) (2023)
- [Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research](https://mlsanity.com/paper/2310.08710/) (2023)
- [End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances](https://mlsanity.com/paper/1911.10868/) (2019)
- [DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2308.00398/) (2023)
- [Diffusion-Based Planning for Autonomous Driving with Flexible Guidance](https://mlsanity.com/paper/2501.15564/) (2025)
- [Learning from All Vehicles](https://mlsanity.com/paper/2203.11934/) (2022)

## Built on by (most cited first, 30 of 35)

- [Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)](https://mlsanity.com/paper/2505.16394/) (2025)
- [SimScale: Learning to Drive via Real-World Simulation at Scale](https://mlsanity.com/paper/2511.23369/) (2025)
- [Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving](https://mlsanity.com/paper/2509.20109/) (2025)
- [LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving](https://mlsanity.com/paper/2512.20563/) (2025)
- [Fail2Drive: Benchmarking Closed-Loop Driving Generalization](https://mlsanity.com/paper/2604.08535/) (2026)
- [Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer](https://mlsanity.com/paper/2510.24108/) (2025)
- [PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving](https://mlsanity.com/paper/2511.07292/) (2025)
- [When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks](https://mlsanity.com/paper/2510.14677/) (2025)
- [Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving](https://mlsanity.com/paper/2605.10034/) (2026)
- [Scaling Self-Play for End-to-End Driving](https://mlsanity.com/paper/2606.19641/) (2026)
- [RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time](https://mlsanity.com/paper/2603.28522/) (2026)
- [DriveZero: End-to-End Driving Beyond Human Demonstrations](https://mlsanity.com/paper/2609.06055/) (2026)
- [Constrained Group Relative Policy Optimization](https://mlsanity.com/paper/2602.05863/) (2026)
- [CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies](https://mlsanity.com/paper/2605.04470/) (2026)
- [CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.02841/) (2026)
- [End-to-End Crop Row Navigation via LiDAR-Based Deep Reinforcement Learning](https://mlsanity.com/paper/2509.18608/) (2025)
- [Driving is a Game: Combining Planning and Prediction with Bayesian Iterative Best Response](https://mlsanity.com/paper/2512.03936/) (2025)
- [MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving](https://mlsanity.com/paper/2605.14201/) (2026)
- [TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale](https://mlsanity.com/paper/2607.13028/) (2026)
- [OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher](https://mlsanity.com/paper/2609.20756/) (2026)
- [Benchmarking Autonomous Driving Planners Across Leaderboards: A Unified CARLA-Based Evaluation](https://mlsanity.com/paper/2509.22754/) (2025)
- [Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving](https://mlsanity.com/paper/2603.20230/) (2026)
- [Learning Dexterous Grasping from Sparse Taxonomy Guidance](https://mlsanity.com/paper/2604.04138/) (2026)
- [Dynamics Distillation for Efficient and Transferable Control Learning](https://mlsanity.com/paper/2605.01516/) (2026)
- [DriveSafer: End-to-End Autonomous Driving with Safety Guidance](https://mlsanity.com/paper/2605.16737/) (2026)
- [Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/2605.30576/) (2026)
- [PlanRL: A Trajectory Planning Architecture for Reinforcement Learning-based Driving Experts](https://mlsanity.com/paper/2606.26858/) (2026)
- [LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields](https://mlsanity.com/paper/2606.31941/) (2026)
- [Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning](https://mlsanity.com/paper/2607.07844/) (2026)
- [nuTruck: Benchmarking Autonomous Driving Planning for Distributed Electric-drive Trucks](https://mlsanity.com/paper/2607.13704/) (2026)

## Abstract (arXiv)

We investigate reinforcement learning (RL) for privileged planning in autonomous driving. State-of-the-art approaches for this task are rule-based, but these methods do not scale to the long tail. RL, on the other hand, is scalable and does not suffer from compounding errors like imitation learning. Contemporary RL approaches for driving use complex shaped rewards that sum multiple individual rewards, eg~progress, position, or orientation rewards. We show that PPO fails to optimize a popular version of these rewards when the mini-batch size is increased, which limits the scalability of these approaches. Instead, we propose a new reward design based primarily on optimizing a single intuitive reward term: route completion. Infractions are penalized by terminating the episode or multiplicatively reducing route completion. We find that PPO scales well with higher mini-batch sizes when trained with our simple reward, even improving performance. Training with large mini-batch sizes enables efficient scaling via distributed data parallelism. We scale PPO to 300M samples in CARLA and 500M samples in nuPlan with a single 8-GPU node. The resulting model achieves 64 DS on the CARLA longest6 v2 benchmark, outperforming other RL methods with more complex rewards by a large margin. Requiring only minimal adaptations from its use in CARLA, the same method is the best learning-based approach on nuPlan. It scores 91.3 in non-reactive and 90.6 in reactive traffic on the Val14 benchmark while being an order of magnitude faster than prior work.