Update reinforcement_q_learning.py (pytorch#429)

kli-casia · soumith · commit e7b036a579b0 · 2019-05-27T03:36:41.000-04:00
diff --git a/intermediate_source/reinforcement_q_learning.py b/intermediate_source/reinforcement_q_learning.py
@@ -100,7 +100,7 @@
 # For this, we're going to need two classses:
 #
 # -  ``Transition`` - a named tuple representing a single transition in
-#    our environment. It maps essentially maps (state, action) pairs
+#    our environment. It essentially maps (state, action) pairs
 #    to their (next_state, reward) result, with the state being the
 #    screen difference image as described later on.
 # -  ``ReplayMemory`` - a cyclic buffer of bounded size that holds the

Original file line number	Diff line number	Diff line change
`@@ -100,7 +100,7 @@`
`100`	`100`	`# For this, we're going to need two classses:`
`101`	`101`	`#`
`102`	`102`	# - ``Transition`` - a named tuple representing a single transition in
`103`		`-# our environment. It maps essentially maps (state, action) pairs`
	`103`	`+# our environment. It essentially maps (state, action) pairs`
`104`	`104`	`# to their (next_state, reward) result, with the state being the`
`105`	`105`	`# screen difference image as described later on.`
`106`	`106`	# - ``ReplayMemory`` - a cyclic buffer of bounded size that holds the