A Framework for Constrained and Adaptive Behavior-Based Agents
This work addresses the challenge of enabling adaptive behavior in constrained agents for domains like robotics and games, though it appears incremental as it builds on existing Behavior Trees and Reinforcement Learning methods.
The paper tackles the problem of adding learning capabilities to constrained agents in robotics and games by proposing a framework that integrates Reinforcement Learning nodes into Behavior Trees, and shows empirically that these learning nodes do not disrupt other nodes while ensuring convergence.
Behavior Trees are commonly used to model agents for robotics and games, where constrained behaviors must be designed by human experts in order to guarantee that these agents will execute a specific chain of actions given a specific set of perceptions. In such application areas, learning is a desirable feature to provide agents with the ability to adapt and improve interactions with humans and environment, but often discarded due to its unreliability. In this paper, we propose a framework that uses Reinforcement Learning nodes as part of Behavior Trees to address the problem of adding learning capabilities in constrained agents. We show how this framework relates to Options in Hierarchical Reinforcement Learning, ensuring convergence of nested learning nodes, and we empirically show that the learning nodes do not affect the execution of other nodes in the tree.