Update reinforcement_q_learning.py (#2867)

nevinaragam · web-flow · commit e50392cf0976 · 2024-05-13T09:45:02.000-07:00
diff --git a/intermediate_source/reinforcement_q_learning.py b/intermediate_source/reinforcement_q_learning.py
@@ -227,7 +227,7 @@ def forward(self, x):
 # This cell instantiates our model and its optimizer, and defines some
 # utilities:
 #
-# -  ``select_action`` - will select an action accordingly to an epsilon
+# -  ``select_action`` - will select an action according to an epsilon
 #    greedy policy. Simply put, we'll sometimes use our model for choosing
 #    the action, and sometimes we'll just sample one uniformly. The
 #    probability of choosing a random action will start at ``EPS_START``

Original file line number	Diff line number	Diff line change
`@@ -227,7 +227,7 @@ def forward(self, x):`
`227`	`227`	`# This cell instantiates our model and its optimizer, and defines some`
`228`	`228`	`# utilities:`
`229`	`229`	`#`
`230`		-# - ``select_action`` - will select an action accordingly to an epsilon
	`230`	+# - ``select_action`` - will select an action according to an epsilon
`231`	`231`	`# greedy policy. Simply put, we'll sometimes use our model for choosing`
`232`	`232`	`# the action, and sometimes we'll just sample one uniformly. The`
`233`	`233`	# probability of choosing a random action will start at ``EPS_START``