Trajectory

Noun · AI & Machine Learning

Definitions

  1. A sequence of states, actions, observations, or decisions taken over time in a learning or agentic environment. Trajectories are central in reinforcement learning and agent evaluation because they capture behavior across steps, not just isolated outputs.

    In plain English: A sequence of steps or states taken by an agent over time.

    Example: "The analysis focused on full trajectories so the team could understand where the agent began drifting off plan instead of only scoring the final answer."

Related Terms