From the 1 of 3 linked papers with an AI index.
3 papers
Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents
Ankita Samaddar, Sandeep Neema, Daniel Balasubramanian +1
The paper proposes an imitation‑learning method to infer the policy of a hidden red‑team attacker in partially observable network environments, and integrates this prediction into…
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…
Resilient Peer-to-peer Learning based on Adaptive Aggregation
Chandreyee Bhowmick, Xenofon Koutsoukos
Collaborative learning in peer-to-peer networks offers the benefits of distributed learning while mitigating the risks associated with single points of failure inherent in centrali…