AI engineering glossary · Reinforcement learning
What is DAgger?
DAgger (also called Dataset Aggregation): An imitation method that runs the learner's own rule, asks an expert to label the situations it reaches, adds them to the training data, and retrains. It fixes the compounding-error problem of pure copying.
DAgger: an example
Round 2: the learner drives, the expert labels correct steering in the spots where the learner wandered off, and the model is retrained.
Related terms
More Reinforcement learning terms
- Deadly triad
- Deep deterministic policy gradient
- Deep Q-network
- Deterministic policy
- Deterministic policy gradient
- Discount factor
- Distributional reinforcement learning
- Double DQN
Where you learn it
DAgger is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.