Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.03142 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917884871049216 |
|---|---|
| author | Gross, Dennis Spieker, Helge |
| author_facet | Gross, Dennis Spieker, Helge |
| contents | Deep reinforcement learning (RL) policies can demonstrate unsafe behaviors and are challenging to interpret. To address these challenges, we combine RL policy model checking--a technique for determining whether RL policies exhibit unsafe behaviors--with co-activation graph analysis--a method that maps neural network inner workings by analyzing neuron activation patterns--to gain insight into the safe RL policy's sequential decision-making. This combination lets us interpret the RL policy's inner workings for safe decision-making. We demonstrate its applicability in various experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies Gross, Dennis Spieker, Helge Artificial Intelligence Machine Learning Deep reinforcement learning (RL) policies can demonstrate unsafe behaviors and are challenging to interpret. To address these challenges, we combine RL policy model checking--a technique for determining whether RL policies exhibit unsafe behaviors--with co-activation graph analysis--a method that maps neural network inner workings by analyzing neuron activation patterns--to gain insight into the safe RL policy's sequential decision-making. This combination lets us interpret the RL policy's inner workings for safe decision-making. We demonstrate its applicability in various experiments. |
| title | Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.03142 |