# Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World

arXiv: https://arxiv.org/abs/2009.11212 · HTML: https://mlsanity.com/paper/2009.11212/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies](https://mlsanity.com/paper/2112.11937/) (2021)
- [Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications](https://mlsanity.com/paper/2107.11750/) (2021)
- [A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Driving](https://mlsanity.com/paper/2304.08235/) (2023)
- [Autonomous Driving Small-Scale Cars: A Survey of Recent Development](https://mlsanity.com/paper/2404.06229/) (2024)
- [Deployable Reinforcement Learning with Variable Control Rate](https://mlsanity.com/paper/2401.09286/) (2024)
- [Reinforcement Learning with Elastic Time Steps](https://mlsanity.com/paper/2402.14961/) (2024)
- [Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-agent Urban Driving Environment](https://mlsanity.com/paper/2112.11947/) (2021)
- [Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning](https://mlsanity.com/paper/2203.12048/) (2022)
- [CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving](https://mlsanity.com/paper/2503.22248/) (2025)
- [Automatic Evaluation of Excavator Operators using Learned Reward Functions](https://mlsanity.com/paper/2211.07941/) (2022)
- [Staged Reinforcement Learning for Complex Tasks through Decomposed Environments](https://mlsanity.com/paper/2311.02746/) (2023)
- [A Sim-to-Real Vision-based Lane Keeping System for a 1:10-scale Autonomous Vehicle](https://mlsanity.com/paper/2409.18097/) (2024)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) has been successfully used to solve different challenges, e.g. complex board and computer games, recently. However, solving real-world robotics tasks with DRL seems to be a more difficult challenge. The desired approach would be to train the agent in a simulator and transfer it to the real world. Still, models trained in a simulator tend to perform poorly in real-world environments due to the differences. In this paper, we present a DRL-based algorithm that is capable of performing autonomous robot control using Deep Q-Networks (DQN). In our approach, the agent is trained in a simulated environment and it is able to navigate both in a simulated and real-world environment. The method is evaluated in the Duckietown environment, where the agent has to follow the lane based on a monocular camera input. The trained agent is able to run on limited hardware resources and its performance is comparable to state-of-the-art approaches.