Pythonic edits

Replaced `zip(range(len(..)), ..)` with `enumerate(..)`

chapter07/random_walk.py

@@ -111,8 +111,8 @@ def figure7_2():
     # track the errors for each (step, alpha) combination
     errors = np.zeros((len(steps), len(alphas)))
     for run in tqdm(range(0, runs)):
-        for step_ind, step in zip(range(len(steps)), steps):
-            for alpha_ind, alpha in zip(range(len(alphas)), alphas):
+        for step_ind, step in enumerate(steps):
+            for alpha_ind, alpha in enumerate(alphas):
                 # print('run:', run, 'step:', step, 'alpha:', alpha)
                 value = np.zeros(N_STATES + 2)
                 for ep in range(0, episodes):

chapter08/maze.py

@@ -406,15 +406,15 @@ def figure_8_2():
     steps = np.zeros((len(planning_steps), episodes))
 
     for run in tqdm(range(runs)):
-        for index, planning_step in zip(range(len(planning_steps)), planning_steps):
+        for i, planning_step in enumerate(planning_steps):
             dyna_params.planning_steps = planning_step
             q_value = np.zeros(dyna_maze.q_size)
 
             # generate an instance of Dyna-Q model
             model = TrivialModel()
             for ep in range(episodes):
                 # print('run:', run, 'planning step:', planning_step, 'episode:', ep)
-                steps[index, ep] += dyna_q(q_value, model, dyna_maze, dyna_params)
+                steps[i, ep] += dyna_q(q_value, model, dyna_maze, dyna_params)
 
     # averaging over runs
     steps /= runs

chapter12/random_walk.py

@@ -185,8 +185,8 @@ def parameter_sweep(value_function_generator, runs, lambdas, alphas):
     # track the rms errors
     errors = [np.zeros(len(alphas_)) for alphas_ in alphas]
     for run in tqdm(range(runs)):
-        for lambdaIndex, rate in zip(range(len(lambdas)), lambdas):
-            for alphaIndex, alpha in zip(range(len(alphas[lambdaIndex])), alphas[lambdaIndex]):
+        for lambdaIndex, rate in enumerate(lambdas):
+            for alphaIndex, alpha in enumerate(alphas[lambdaIndex]):
                 valueFunction = value_function_generator(rate, alpha)
                 for episode in range(episodes):
                     random_walk(valueFunction)