From 7871167919a11709bbbbc444f20bde5a6df8363b Mon Sep 17 00:00:00 2001 From: worthy7 Date: Tue, 19 Nov 2024 17:06:54 +0900 Subject: [PATCH] Update train_agent.md --- docs/introduction/train_agent.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/introduction/train_agent.md b/docs/introduction/train_agent.md index 88d174be2..48ff90cd5 100644 --- a/docs/introduction/train_agent.md +++ b/docs/introduction/train_agent.md @@ -105,7 +105,7 @@ class BlackjackAgent: ## Training the agent -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 it's Q-values after each episode. The agent will have to experience a lot of episodes to explore the environment sufficiently. +To train the agent, we will let the agent play one episode (one complete game is called an episode) at a time and update it's Q-values after each action taken during the episode. The agent will have to experience a lot of episodes to explore the environment sufficiently. ```python # hyperparameters