# Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

arXiv: https://arxiv.org/abs/1610.03295 · HTML: https://mlsanity.com/paper/1610.03295/

## Key facts

- Cited by 311 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2016.

## Built on by (most cited first, 30 of 311)

- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients](https://mlsanity.com/paper/2109.13333/) (2021)
- [V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL](https://mlsanity.com/paper/2110.14555/) (2021)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving](https://mlsanity.com/paper/2403.04133/) (2024)
- [MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning](https://mlsanity.com/paper/2502.18439/) (2025)
- [A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends](https://mlsanity.com/paper/2407.07403/) (2024)
- [Federated Reinforcement Learning: Techniques, Applications, and Open Challenges](https://mlsanity.com/paper/2108.11887/) (2021)
- [Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates](https://mlsanity.com/paper/2101.05436/) (2021)
- [On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method](https://mlsanity.com/paper/2102.08607/) (2021)
- [SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies](https://mlsanity.com/paper/2109.13602/) (2021)
- [BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning](https://mlsanity.com/paper/2105.00579/) (2021)
- [LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions](https://mlsanity.com/paper/2405.11106/) (2024)
- [A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://mlsanity.com/paper/2101.01993/) (2021)
- [Safe Multi-Agent Reinforcement Learning via Shielding](https://mlsanity.com/paper/2101.11196/) (2021)
- [Decentralized Q-Learning in Zero-sum Markov Games](https://mlsanity.com/paper/2106.02748/) (2021)
- [Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence](https://mlsanity.com/paper/2202.04129/) (2022)
- [MARFT: Multi-Agent Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.16129/) (2025)
- [The Complexity of Markov Equilibrium in Stochastic Games](https://mlsanity.com/paper/2204.03991/) (2022)
- [The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces](https://mlsanity.com/paper/2106.03352/) (2021)
- [Safe Reinforcement Learning Using Advantage-Based Intervention](https://mlsanity.com/paper/2106.09110/) (2021)
- [A Survey of Constraint Formulations in Safe Reinforcement Learning](https://mlsanity.com/paper/2402.02025/) (2024)
- [Towards General Function Approximation in Zero-Sum Markov Games](https://mlsanity.com/paper/2107.14702/) (2021)
- [CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing](https://mlsanity.com/paper/2106.09292/) (2021)
- [Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games](https://mlsanity.com/paper/2110.05682/) (2021)
- [AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learning](https://mlsanity.com/paper/2404.06345/) (2024)
- [Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning](https://mlsanity.com/paper/2107.04050/) (2021)
- [Multi-Agent Coordination across Diverse Applications: A Survey](https://mlsanity.com/paper/2502.14743/) (2025)
- [On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2110.05707/) (2021)

## Abstract (arXiv)

Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured urban roadways. Since there are many possible scenarios, manually tackling all possible cases will likely yield a too simplistic policy. Moreover, one must balance between unexpected behavior of other drivers/pedestrians and at the same time not to be too defensive so that normal traffic flow is maintained. In this paper we apply deep reinforcement learning to the problem of forming long term driving strategies. We note that there are two major challenges that make autonomous driving different from other robotic tasks. First, is the necessity for ensuring functional safety - something that machine learning has difficulty with given that performance is optimized at the level of an expectation over many instances. Second, the Markov Decision Process model often used in robotics is problematic in our case because of unpredictable behavior of other agents in this multi-agent scenario. We make three contributions in our work. First, we show how policy gradient iterations can be used without Markovian assumptions. Second, we decompose the problem into a composition of a Policy for Desires (which is to be learned) and trajectory planning with hard constraints (which is not learned). The goal of Desires is to enable comfort of driving, while hard constraints guarantees the safety of driving. Third, we introduce a hierarchical temporal abstraction we call an "Option Graph" with a gating mechanism that significantly reduces the effective horizon and thereby reducing the variance of the gradient estimation even further.