- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper investigates whether transparent policies are safer to deploy. In a dual-source inventory control experiment, the authors show that exact attribution does not guarantee robustness, stable interaction rankings, or operational relevance.
Critical strengths
- The motivation in this paper is interesting.
- The structural-zero interaction analysis is convincing.
Critical weaknesses
- The paper only shows several observations that have already been discussed in previous research [1-3]
- Table 6 evaluates the training reward function on held-out disruptions. However, it does not distinguish insufficient optimization from poor out-of-distribution generalization.
- The test is not realistic. Specifically, the reference trajectory uses a constant action that differs substantially from the learned policies' behavior.
[1] Sundararajan, Mukund, and Amir Najmi. "The many Shapley values for model explanation." International conference on machine learning. PMLR, 2020.
[2] Beechey, Daniel, Thomas MS Smith, and Özgür Şimşek. "Explaining reinforcement learning with shapley values." International Conference on Machine Learning. PMLR, 2023.
[3] Lengerich, Benjamin, et al. "Purifying interaction effects with the functional anova: An efficient algorithm for recovering identifiable additive models." International Conference on Artificial Intelligence and Statistics. PMLR, 2020.
Questions for authors
- What will happen if increasing the PPO training budget?