- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes an information-theoretic rate-distortion framework for adversarial attacks against reinforcement learning agents, aiming to reduce the information that perturbed observations reveal about the true environment under a distortion budget.
Critical strengths
-
The authors provide a relatively comprehensive theoretical analysis.
-
The authors formulate and quantify perturbations from an information-theoretic perspective.
Critical weaknesses
-
The writing needs further improvement. For example, the motivating example in the Introduction is not easy to follow.
-
The paper provides only theoretical results and lacks experimental validation.
-
The types of perturbations considered lack a clear connection to the physical world.
Questions for authors
-
Does the type of environmental uncertainty defined in this paper exist in practical settings? In standard MDPs and methods such as SA-MDP, state transitions are also stochastic rather than deterministic. How does the notion of uncertainty in this paper differ from that considered in these existing works?
-
In methods such as SA-MDP and PA-AD, perturbations are typically constrained by an norm with a small magnitude, allowing them to be regarded as noise. Does the budget-constrained attack proposed in this paper ensure that the perturbations remain reasonable and imperceptible?
-
Can the effectiveness of the proposed method be validated through practical experiments, for example, in simple RL environments such as Atari?