From 442899a1ab4f20caa5f4a0062821af182119cc3d Mon Sep 17 00:00:00 2001 From: Kai Li <1196594711@qq.com> Date: Wed, 30 Jan 2019 17:32:31 +0800 Subject: [PATCH] Update reinforcement_q_learning.py --- intermediate_source/reinforcement_q_learning.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/intermediate_source/reinforcement_q_learning.py b/intermediate_source/reinforcement_q_learning.py index cac4842795b..c475c37c5f3 100644 --- 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