AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics

arXiv · AI, language, vision and robotics · article · Nov 10, 2026 · UTC

Reinforcement learning from formal specifications often separates task definition, reward shaping, curriculum design, and policy diagnostics into different mathematical objects. This fragmentation requires additional conversion steps and discards structure already present in the specification, such as subtask boundaries, ordering constraints, and quantitative measures. We introduce TBTCL (Temporal Behavior Tree Centric Learning), a framework that uses Temporal Behavior Trees (TBTs) as a unified interface for specification-guided reinforcement learning. A single TBT specifies the task, induces

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-11-11T20:22:53.617Z. This is not the publication date.