Abstract
This research explores an emerging approach, the adversarial policy learning paradigm, that aims to increase safety and robustness in deep reinforcement learning models for automated driving. We propose an iterative procedure to train an adversarial agent acting in a highway-simulated environment to attack a victim agent that is to be improved. Each training iteration consists of two phases. The adversarial agent is first trained to disrupt the victim-agent policy. The victim model is then trained to overcome the defects observed by the attack from the adversarial agent. The experimental results demonstrate that the victim agent trained with adversarial attacks outperforms the original agent.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Folkers A, Rick M, Buskens C (2019) Controlling an autonomous vehicle with deep reinforcement learning. In: 2019 IEEE intelligent vehicles symposium (IV), pp 2025–2031. IEEE, Paris, France
Bellotti F, Lazzaroni L, Capello A, Cossu M, De Gloria A, Berta R (2023) Explaining a deep reinforcement learning (DRL)-based automated driving agent in highway simulations. IEEE Access. 11:28522–28550. https://doi.org/10.1109/ACCESS.2023.3259544
Lazzaroni L, Bellotti F, Capello A, Cossu M, De Gloria A, Berta R (2023) Deep reinforcement learning for automated car parking. In: Berta R, De Gloria A (eds) Applications in electronics pervading industry, environment and Society. Springer Nature Switzerland, Cham, pp 125–130
Zhang H, Chen H, Xiao C, Li B, Liu M, Boning D, Hsieh C-J (2021) Robust deep reinforcement learning against adversarial perturbations on state observations. http://arxiv.org/abs/2003.08938
Pinto L, Davidson J, Sukthankar R, Gupta A (2017) Robust adversarial reinforcement learning. http://arxiv.org/abs/1703.02702
Gleave A, Dennis M, Wild C, Kant N, Levine S, Russell S (2021) Adversarial policies: attacking deep reinforcement learning. http://arxiv.org/abs/1905.10615
Leurent E (2018) An environment for autonomous driving decision-making. https://github.com/eleurent/highway-env
Goodfellow I et al (2020) Generative adversarial networks. Commun ACM 63:139–144. https://doi.org/10.1145/3422622
Campodonico G et al (2021) Adapting autonomous agents for automotive driving games. In: De Rosa F, Marfisi Schottman I, Baalsrud Hauge J, Bellotti F, Dondio P, Romero M (eds) Games and learning alliance. Springer International Publishing, Cham, pp 101–110
Pighetti A et al (2022) High-level decision-making non-player vehicles. In: Kiili K, Antti K, de Rosa F, Dindar M, Kickmeier-Rust M, Bellotti F (eds) Games and learning alliance. Springer International Publishing, Cham, pp 223–233
Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) OpenAI Gym. http://arxiv.org/abs/1606.01540
Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. http://arxiv.org/abs/1707.06347
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pighetti, A. et al. (2024). Investigating Adversarial Policy Learning for Robust Agents in Automated Driving Highway Simulations. In: Bellotti, F., et al. Applications in Electronics Pervading Industry, Environment and Society. ApplePies 2023. Lecture Notes in Electrical Engineering, vol 1110. Springer, Cham. https://doi.org/10.1007/978-3-031-48121-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-48121-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48120-8
Online ISBN: 978-3-031-48121-5
eBook Packages: EngineeringEngineering (R0)