Fetching the paper…

Reading the bibliography…

2020

On the Robustness of Cooperative Multi-Agent Reinforcement Learning

Lin, Jieyu, Dzeparoska, Kristina, Zhang, Sai Qian et al.

Original
PDF
Post on X

Understand

In cooperative multi-agent reinforcement learning (c-MARL), agents learn to cooperatively take actions as a team to maximize a total team reward.

We analyze the robustness of c-MARL to adversaries capable of attacking one of the agents on a team.
Through the ability to manipulate this agent's observations, the adversary seeks to decrease the total team reward.
Attacking c-MARL is challenging for three reasons: first, it is difficult to estimate team rewards or how they are impacted by an agent mispredicting; second, models are non-differentiable; and third, the feature space is low-dimensional.

On the Robustness of Cooperative Multi-Agent Reinforcement Learning · Around

Built on

M. Wiering, “Multi-agent reinforcement learning for traffic light control,” in Machine Learning: Proceedings of the Seventeenth International Conference (ICML’2000) , 2000, pp. 1151–1158
2000
Earlier work this paper cites.
I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” arXiv preprint arXiv:1412.6572 , 2014
Original
2014
Earlier work this paper cites.
S. Shalev-Shwartz, S. Shammah, and A. Shashua, “Safe, multi-agent, reinforcement learning for autonomous driving,” arXiv preprint arXiv:1610.03295 , 2016
Original
2016
Earlier work this paper cites.
F. A. Oliehoek, C. Amato et al. , A concise introduction to decentralized POMDPs . Springer, 2016, vol. 1
2016
Earlier work this paper cites.
A. Kurakin, I. Goodfellow, and S. Bengio, “Adversarial examples in the physical world,” arXiv preprint arXiv:1607.02533 , 2016
Original
2016
Earlier work this paper cites.
N. Papernot, P. McDaniel, S. Jha, M. Fredrikson, Z. B. Celik, and A. Swami, “The limitations of deep learning in adversarial settings,” in 2016 IEEE European Symposium on Security and Privacy (EuroS&P) . IEEE, 2016, pp. 372–387
2016
Earlier work this paper cites.
S. Huang, N. Papernot, I. Goodfellow, Y. Duan, and P. Abbeel, “Adversarial attacks on neural network policies,” arXiv preprint arXiv:1702.02284 , 2017
Original
2017
Earlier work this paper cites.

Similar

N. Papernot, P. McDaniel, I. Goodfellow, S. Jha, Z. B. Celik, and A. Swami, “Practical black-box attacks against machine learning,” in Proceedings of the 2017 ACM on Asia conference on computer and communications security . ACM, 2017, pp. 506–519
2017
Cited alongside, same era.
P.-Y. Chen, H. Zhang, Y. Sharma, J. Yi, and C.-J. Hsieh, “Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models,” in Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security . ACM, 2017, pp. 15–26
2017
Cited alongside, same era.
N. Carlini and D. Wagner, “Towards evaluating the robustness of neural networks,” in 2017 IEEE Symposium on Security and Privacy (SP) . IEEE, 2017, pp. 39–57
2017
Cited alongside, same era.
Y.-C. Lin, Z.-W. Hong, Y.-H. Liao, M.-L. Shih, M.-Y. Liu, and M. Sun, “Tactics of adversarial attack on deep reinforcement learning agents,” arXiv preprint arXiv:1703.06748 , 2017
Original
2017

Then

A. Athalye, N. Carlini, and D. Wagner, “Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples,” arXiv preprint arXiv:1802.00420 , 2018
Original
2018
Later among the works it cites.
T. Rashid, M. Samvelyan, C. S. De Witt, G. Farquhar, J. Foerster, and S. Whiteson, “Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning,” arXiv preprint arXiv:1803.11485 , 2018
Original
2018
Later among the works it cites.
S. Q. Zhang, Q. Zhang, and J. Lin, “Efficient communication in multi-agent reinforcement learning via variance based control,” in Advances in Neural Information Processing Systems , 2019, pp. 3230–3239
2019
Later among the works it cites.
A. Gleave, M. Dennis, N. Kant, C. Wild, S. Levine, and S. Russell, “Adversarial policies: Attacking deep reinforcement learning,” arXiv preprint arXiv:1905.10615 , 2019
Original
2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

V. Behzadan and A. Munir, “Vulnerability of deep reinforcement learning to policy induction attacks,” in International Conference on Machine Learning and Data Mining in Pattern Recognition . Springer, 2017, pp. 262–275

2017

Cited alongside, same era.

C. de Vrieze, S. Barratt, D. Tsai, and A. Sahai, “Cooperative multi-agent reinforcement learning for low-level wireless communication,” arXiv preprint arXiv:1801.04541 , 2018

2018

Cited alongside, same era.

M. Samvelyan, T. Rashid, C. Schroeder de Witt, G. Farquhar, N. Nardelli, T. G. Rudner, C.-M. Hung, P. H. Torr, J. Foerster, and S. Whiteson, “The starcraft multi-agent challenge,” in Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems . International Foundation for Autonomous Agents and Multiagent Systems, 2019, pp. 2186–2188

2019

Later among the works it cites.

Y. Zhao, I. Shumailov, H. Cui, X. Gao, R. Mullins, and R. Anderson, “Blackbox attacks on reinforcement learning agents using approximated temporal information,” arXiv preprint arXiv:1909.02918 , 2019

2019

Later among the works it cites.