From 628b8297e6edbf747486db3b40df9e4b30e3d32d Mon Sep 17 00:00:00 2001 From: Anna Klepova Date: Sun, 9 Jun 2019 01:06:09 +0300 Subject: [PATCH] Fix exercise 6.1 description, it's confusing gamma is discount rate, not learning rate these are different things learning rate is alpha, there is no learning rate in Policy Evaluation --- labs/notebooks/reinforcement_learning/exercises_1_4.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/labs/notebooks/reinforcement_learning/exercises_1_4.ipynb b/labs/notebooks/reinforcement_learning/exercises_1_4.ipynb index ca06ccd9..5758e894 100644 --- a/labs/notebooks/reinforcement_learning/exercises_1_4.ipynb +++ b/labs/notebooks/reinforcement_learning/exercises_1_4.ipynb @@ -33,7 +33,7 @@ "for i in range(20):\n", " print(state_value_function)\n", " \n", - " state_value_function=#TODO: Implement the Policy Evaluation Update with a Learning Rate of 0.1\n", + " state_value_function=#TODO: Implement the Policy Evaluation Update with a Discount Rate of 0.1\n", "print(state_value_function)" ] }, @@ -54,7 +54,7 @@ "metadata": {}, "outputs": [], "source": [ - "solution=#TODO: Implement the linear programming solution with a learning rate of 0.1\n", + "solution=#TODO: Implement the linear programming solution with a discount rate of 0.1\n", "print(solution)" ] },