Summary of Behavior-targeted Attack on Reinforcement Learning with Limited Access to Victim’s Policy, by Shojiro Yamabe et al.
Behavior-Targeted Attack on Reinforcement Learning with Limited Access to Victim’s Policy
by Shojiro Yamabe, Kazuto Fukuchi, Ryoma Senda, Jun Sakuma
First submitted to arxiv on: 6 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study proposes a novel approach for manipulating the behavior of reinforcement learning agents without requiring white-box access or environment-specific heuristics. The method, formulated as a bi-level optimization problem, can be solved using an existing imitation learning algorithm in both black-box and no-box settings. Empirical evaluations on several benchmarks demonstrate superior attack performance compared to baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study looks at ways to control the behavior of machines that learn from experience, by adding fake information to what they see. This is useful for testing how well these machines can be controlled or fooled. The researchers developed a new method that doesn’t need special knowledge about the situation where it’s being used. They tested their idea on different scenarios and found that it works better than other approaches. |
Keywords
» Artificial intelligence » Optimization » Reinforcement learning
