Skip to content

Instantly share code, notes, and snippets.

"""
Expected Value SARSA
This file builds upon the same functions as Q-learning agent (qlearning.py).
[assignment]
The only thing you must implement is the getValue method.
- Recall that V(s) in SARSA is not the maximal but the expected Q-value.
- The expectation should be done under agent's policy (e-greedy).
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.