GRAIL: Goal Recognition Alignment through Imitation Learning

Aligning AI systems with human intentions requires understanding an agent’s goals from its behavior. Existing goal recognition methods typically rely on an approximately optimal goal-oriented policy representation, which may differ from the actor’s true behavior and hinder the accurate recognition of their goal. To address this gap, this paper introduces Goal Recognition Alignment through ImitationLearning(GRAIL), whichleveragesimitationlearningand inverse reinforcement learning to learn one goal-directed policy for each candidate goal directly from (potentially suboptimal) demonstration trajectories. By scoring an observed partial trajectory with each learned goal-directed policy in a single forward pass, GRAIL retains the one-shot inference capability of classical goal recognition while leveraging learned policies that can capture suboptimal and systematically biased behavior. Empirical evaluations show that GRAIL outperforms standard reinforcement learning-based GRtechniquesinrecognizingbothsuboptimalandbiasedbehaviors in controlled, closed-set goal environments.

Authors

• Osher Elhadad Department of Computer Science, Bar Ilan University
• Felipe Meneguzzi Department of Computer Science, Aberdeen University
• Reuth Mirsky Department of Computer Science, Tufts University

Keywords

• Goal Recognition
• Agent Modeling
• Imitation Learning
• Goal Alignment
• Reinforcement Learning