AI engineering glossary · Reinforcement learning
What is eligibility trace?
Eligibility trace: A short-term memory that records how recently and how often each situation or parameter was involved, so a single surprise can update many earlier steps at once in proportion to their responsibility. It speeds up credit assignment in temporal-difference methods.
Eligibility trace: an example
After a big surprise, the last step's value moves by the full error, the one before by lambda*gamma times the error, and so on.
Related terms
More Reinforcement learning terms
- Entropy regularisation
- Environment
- Episode
- Episodic task
- Epsilon-greedy
- Experience replay
- Exploitation
- Exploration
Where you learn it
Eligibility trace is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.