AI engineering glossary · Reinforcement learning
What is experience replay?
Experience replay (also called Replay buffer): A store of past transitions from which random mini-batches are sampled for training. It breaks the correlation between consecutive steps and lets each transition be reused many times, improving stability and data efficiency for off-policy methods.
Experience replay: an example
A buffer holds the last 1 million transitions; each update samples 32 at random.
Related terms
More Reinforcement learning terms
- Exploitation
- Exploration
- Exploration-exploitation trade-off
- Function approximation
- Goal-conditioned reinforcement learning
- Greedy policy
- Hierarchical reinforcement learning
- Hindsight experience replay
Where you learn it
Experience replay is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.