5 papers
Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs
Nicholas Potteiger, Ankita Samaddar, Taylor T. Johnson +1
Decomposing complex tasks into a sequence of simpler subtasks can improve learning efficiency for an autonomous agent. Reinforcement learning (RL) can be used to optimize agent pol…
Training RL Agents for Multi-Objective Network Defense Tasks
Andres Molina-Markham, Luis Robaina, Sean Steinle +6
Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (…
Out-of-Distribution Detection for Neurosymbolic Autonomous Cyber Agents
Ankita Samaddar, Nicholas Potteiger, Xenofon Koutsoukos
Autonomous agents for cyber applications take advantage of modern defense techniques by adopting intelligent agents with conventional and learning-enabled components. These intelli…
Verification of Behavior Trees with Contingency Monitors
Serena S. Serbinowska, Nicholas Potteiger, Anne M. Tumlin +1
Behavior Trees (BTs) are high level controllers that have found use in a wide range of robotics tasks. As they grow in popularity and usage, it is crucial to ensure that the approp…
Designing Robust Cyber-Defense Agents with Evolving Behavior Trees
Nicholas Potteiger, Ankita Samaddar, Hunter Bergstrom +1
Modern network defense can benefit from the use of autonomous systems, offloading tedious and time-consuming work to agents with standard and learning-enabled components. These age…