AI engineering glossary · Reinforcement learning
What is entropy regularisation?
Entropy regularisation: Adding a bonus proportional to the randomness of the decision rule to the training objective, so probabilities do not collapse to a single choice too soon. Entropy is H = - sum of p * log p, highest for uniform probabilities.
Entropy regularisation: an example
Uniform probabilities over 4 actions have entropy ln 4 = 1.39; probabilities (0.97, 0.01, 0.01, 0.01) have about 0.17.
Related terms
More Reinforcement learning terms
- Environment
- Episode
- Episodic task
- Epsilon-greedy
- Experience replay
- Exploitation
- Exploration
- Exploration-exploitation trade-off
Where you learn it
Entropy regularisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.