# Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms

arXiv: https://arxiv.org/abs/2506.08192 · HTML: https://mlsanity.com/paper/2506.08192/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 5 of 5)

- [Network Environment Design for Autonomous Cyberdefense](https://mlsanity.com/paper/2103.07583/) (2021)
- [On Autonomous Agents in a Cyber Defence Environment](https://mlsanity.com/paper/2309.07388/) (2023)
- [Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies](https://mlsanity.com/paper/2211.15557/) (2022)
- [Automated Cyber Defence: A Review](https://mlsanity.com/paper/2303.04926/) (2023)
- [CybORG: An Autonomous Cyber Operations Research Gym](https://mlsanity.com/paper/2002.10667/) (2020)

## Built on by (most cited first, 2 of 2)

- [Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions](https://mlsanity.com/paper/2509.10983/) (2025)
- [SubstratumGraphEnv: Reinforcement Learning Environment (RLE) for Modeling System Attack Paths](https://mlsanity.com/paper/2603.01340/) (2026)

## Abstract (arXiv)

We analyze two open source deep reinforcement learning agents submitted to the CAGE Challenge 2 cyber defense challenge, where each competitor submitted an agent to defend a simulated network against each of several provided rules-based attack agents. We demonstrate that one can gain interpretability of agent successes and failures by simplifying the complex state and action spaces and by tracking important events, shedding light on the fine-grained behavior of both the defense and attack agents in each experimental scenario. By analyzing important events within an evaluation episode, we identify patterns in infiltration and clearing events that tell us how well the attacker and defender played their respective roles; for example, defenders were generally able to clear infiltrations within one or two timesteps of a host being exploited. By examining transitions in the environment's state caused by the various possible actions, we determine which actions tended to be effective and which did not, showing that certain important actions are between 40% and 99% ineffective. We examine how decoy services affect exploit success, concluding for instance that decoys block up to 94% of exploits that would directly grant privileged access to a host. Finally, we discuss the realism of the challenge and ways that the CAGE Challenge 4 has addressed some of our concerns.