# CORAL: Curriculum-Optimized Reward Adaptation for LiDAR-Based Goal-Directed Urban Driving

arXiv: https://arxiv.org/abs/2608.14332 · HTML: https://mlsanity.com/paper/2608.14332/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 14 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, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [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)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views](https://mlsanity.com/paper/2006.05518/) (2020)
- [Emergent Visual Sensors for Autonomous Vehicles](https://mlsanity.com/paper/2205.09383/) (2022)
- [Carl-Lead: Lidar-based End-to-End Autonomous Driving with Contrastive Deep Reinforcement Learning](https://mlsanity.com/paper/2109.08473/) (2021)
- [A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator](https://mlsanity.com/paper/2509.08221/) (2025)
- [Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving](https://mlsanity.com/paper/2306.03220/) (2023)
- [CuRLA: Curriculum Learning Based Deep Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/2501.04982/) (2025)

## Abstract (arXiv)

Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing behaviors at once--reaching a distant goal, tracking a route, avoiding obstacles, obeying signals--and a fixed objective gives no order in which to learn them. This paper presents CORAL, which advances two schedules together: a five-stage curriculum that progressively lengthens routes and tightens behavioral constraints, and a stage-aware reward whose component weights shift emphasis from mission progress toward route following, safety, smoothness, and rule compliance as the task hardens. The policy is a multi-stream actor-critic network trained with Proximal Policy Optimization (PPO) in CARLA on a compact 99-dimensional state pairing a polar LiDAR histogram with vehicle telemetry, ego-frame route geometry, and traffic-rule indicators--no point-cloud encoder, no bird's-eye-view rasterization. Against two PPO baselines under an identical protocol, CORAL reaches the goal in all twenty evaluation episodes on the longest routes under the full set of behavioral constraints, where the baselines reach 5% and 10%; a factorial ablation shows that neither schedule alone matches their combination: removing either lowers both success and route completion, and disabling both drops success to 55%. Trained in one town, the policy transfers zero-shot to seven unseen towns, succeeding in 68-98% of episodes on routes of the same 100-150 m length, with mean lateral deviation below 0.35 m.