Notebook
Concepts I am working to understand, written out.
Folders
FldConceptLnkUpd.
relates · requiresdrag · scroll · dbl-click
Concepts I am working to understand, written out.
Concepts I am working to understand, written out.
updated 2d ago · 3 links · 1,903 words
Replace the expectation in a Bellman backup with a single sampled transition. SARSA, Q learning, and why the noisy iteration still converges.
links: Bellman · Dynamic programming · Policy gradient
requires: Bellman · Dynamic programming
path: MDPs → Bellman → Dynamic programming → TD learning