Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies
Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Gross, Dennis, Spieker, Helge
Institution: Simula Research Laboratory
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4406123718