Abstract | ||
---|---|---|
We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an agent into following an outsider's policy. It is pre-computed, therefore fast inferred, and could thus be usable in a real-time scenario. We show its effectiveness on Atari 2600 games in the novel read-only setting. In this setting, the adversary cannot directly modify the agent's state -its representation of the environment- but can only attack the agent's observation -its perception of the environment. Directly modifying the agent's state would require a write-access to the agent's inner workings and we argue that this assumption is too strong in realistic settings.
|
Year | DOI | Venue |
---|---|---|
2020 | 10.5555/3398761.3398828 | AAMAS '19: International Conference on Autonomous Agents and Multiagent Systems
Auckland
New Zealand
May, 2020 |
DocType | ISBN | Citations |
Conference | 978-1-4503-7518-4 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Léonard Hussenot | 1 | 0 | 2.70 |
Matthieu Geist | 2 | 385 | 44.31 |
Olivier Pietquin | 3 | 664 | 68.60 |