Fix explanation of training agent (#650)

This commit is contained in:
mvhensbergen
2023-08-05 12:35:20 +02:00
committed by GitHub
parent ba348890af
commit 933d481189

View File

@@ -242,8 +242,10 @@ class BlackjackAgent:
# %%
# To train the agent, we will let the agent play one episode (one complete
# game is called an episode) at a time and then update its Q-values after
# each episode. The agent will have to experience a lot of episodes to
# explore the environment sufficiently.
# each step (one single action in a game is called a step).
#
# The agent will have to experience a lot of episodes to explore the
# environment sufficiently.
#
# Now we should be ready to build the training loop.
#