Goal Conditioned

Definitions

1. Describing a model or policy that takes an explicit goal as part of its input so its behavior can adapt to the desired outcome. Goal-conditioned approaches are common in reinforcement learning, planning, and control tasks.

   In plain English: Designed to take a goal as input and adjust behavior toward it.

   Example: "The navigation policy was goal conditioned, so the same model could handle different destinations without retraining."

Related Terms

• Chinchilla Scaling
• Constitutional AI Method
• Context Distillation
• Expert Iteration
• Frozen Embedding
• Gradient-Free Optimization
• Machine Unlearning
• Process Reward Model
• Replay Buffer