AI engineering glossary · Reinforcement learning
What is rainbow?
Rainbow (also called Rainbow DQN): A combined agent that integrates six improvements to the deep Q-network: double learning, prioritised replay, dueling design, multi-step targets, distributional values and noisy layers. It showed that these pieces are complementary on Atari benchmarks.
Rainbow: an example
Ablation studies remove one component at a time to measure its contribution.
Related terms
More Reinforcement learning terms
Where you learn it
Rainbow is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.