Entity · technique

behavior trees with learning-enabled components

techniqueactivebehavior-trees-with-learning-enabled-components-856bf5c9·1 events·first seen Jun 17, 2026

Aliases: behavior trees with learning-enabled components

Co-occurring entities

Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents

More like this (12)

EvalTree Physics-EnhAnced Reinforcement Learning Neural Classification Trees TreeSim inference-time behavioural unlearning Complementary Learning Systems rule-based reinforcement learning rewards Operator Learning tree-of-attacks Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Reinforcement Learning for Code active learning

Recent events (1)

4arXiv · cs.LG·Jun 17, 2026·source ↗

Imitation learning technique infers red agent policy in partially observable cyber-defense environments

Researchers propose a Policy Learning Technique using imitation learning to infer attacker (red agent) policies from network observations and defender actions in partially observable autonomous cyber environments. The method integrates with neurosymbolic cyber-defense agents that use behavior trees with learning-enabled components. Evaluated across diverse simulated scenarios, the approach achieves high prediction accuracy for red agent actions, improving the defender's ability to anticipate intrusions.

AI Safety Research Agent and Tool Ecosystem Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents behavior trees with learning-enabled components