Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit a6edaa1

Browse files
ad71norvig
ad71
authored and
norvig
committed
Minor enhancement to grid_mdp editor (#734)
* Fixed reset function to reset placeholder variables as well * Added functionality to display best policy
1 parent 516eff0 commit a6edaa1

File tree

1 file changed

+27
-5
lines changed

1 file changed

+27
-5
lines changed

‎gui/grid_mdp.py

Lines changed: 27 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -64,6 +64,22 @@ def display(gridmdp, _height, _width):
6464

6565
dialog.mainloop()
6666

67+
def display_best_policy(_best_policy, _height, _width):
68+
''' displays best policy '''
69+
70+
dialog = tk.Toplevel()
71+
dialog.wm_title('Best Policy')
72+
73+
container = tk.Frame(dialog)
74+
container.pack(side=tk.TOP, fill=tk.BOTH, expand=True)
75+
76+
for i in range(max(1, _height)):
77+
for j in range(max(1, _width)):
78+
label = ttk.Label(container, text=_best_policy[i][j], font=('Helvetica', 12, 'bold'))
79+
label.grid(row=i + 1, column=j + 1, padx=3, pady=3)
80+
81+
dialog.mainloop()
82+
6783
def initialize_dialogbox(_width, _height, gridmdp, terminals, buttons):
6884
''' creates dialogbox for initialization '''
6985

@@ -98,7 +114,7 @@ def initialize_dialogbox(_width, _height, gridmdp, terminals, buttons):
98114

99115
btn_apply = ttk.Button(container, text='Apply', command=partial(initialize_update_table, _width, _height, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_term, rbtn_wall))
100116
btn_apply.grid(row=5, column=0, sticky='nsew', pady=5, padx=5)
101-
btn_reset = ttk.Button(container, text='Reset', command=partial(initialize_reset_all, _width, _height, gridmdp, terminals, buttons, label_reward, entry_reward, rbtn_wall, rbtn_term))
117+
btn_reset = ttk.Button(container, text='Reset', command=partial(initialize_reset_all, _width, _height, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_wall, rbtn_term))
102118
btn_reset.grid(row=5, column=1, sticky='nsew', pady=5, padx=5)
103119
btn_ok = ttk.Button(container, text='Ok', command=dialog.destroy)
104120
btn_ok.grid(row=5, column=2, sticky='nsew', pady=5, padx=5)
@@ -146,9 +162,12 @@ def initialize_update_table(_width, _height, gridmdp, terminals, buttons, reward
146162
for j in range(max(1, _width)):
147163
update_table(i, j, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_term, rbtn_wall)
148164

149-
def reset_all(_height, i, j, gridmdp, terminals, buttons, label_reward, entry_reward, rbtn_wall, rbtn_term):
165+
def reset_all(_height, i, j, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_wall, rbtn_term):
150166
''' functionality for reset button '''
151167

168+
reward.set(0.0)
169+
term.set(0)
170+
wall.set(0)
152171
gridmdp[i][j] = 0.0
153172
buttons[i][j].configure(style='TButton')
154173
buttons[i][j].config(text=f'({_height - i - 1}, {j})')
@@ -163,12 +182,12 @@ def reset_all(_height, i, j, gridmdp, terminals, buttons, label_reward, entry_re
163182
rbtn_wall.state(['!focus', '!selected'])
164183
rbtn_term.state(['!focus', '!selected'])
165184

166-
def initialize_reset_all(_width, _height, gridmdp, terminals, buttons, label_reward, entry_reward, rbtn_wall, rbtn_term):
185+
def initialize_reset_all(_width, _height, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_wall, rbtn_term):
167186
''' runs reset_all for all cells '''
168187

169188
for i in range(max(1, _height)):
170189
for j in range(max(1, _width)):
171-
reset_all(_height, i, j, gridmdp, terminals, buttons, label_reward, entry_reward, rbtn_wall, rbtn_term)
190+
reset_all(_height, i, j, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_wall, rbtn_term)
172191

173192
def external_reset(_width, _height, gridmdp, terminals, buttons):
174193
''' reset from edit menu '''
@@ -263,7 +282,7 @@ def dialogbox(i, j, gridmdp, terminals, buttons, _height):
263282

264283
btn_apply = ttk.Button(container, text='Apply', command=partial(update_table, i, j, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_term, rbtn_wall))
265284
btn_apply.grid(row=5, column=0, sticky='nsew', pady=5, padx=5)
266-
btn_reset = ttk.Button(container, text='Reset', command=partial(reset_all, _height, i, j, gridmdp, terminals, buttons, label_reward, entry_reward, rbtn_wall, rbtn_term))
285+
btn_reset = ttk.Button(container, text='Reset', command=partial(reset_all, _height, i, j, gridmdp, terminals, buttons, reward, term, wall, label_reward, entry_reward, rbtn_wall, rbtn_term))
267286
btn_reset.grid(row=5, column=1, sticky='nsew', pady=5, padx=5)
268287
btn_ok = ttk.Button(container, text='Ok', command=dialog.destroy)
269288
btn_ok.grid(row=5, column=2, sticky='nsew', pady=5, padx=5)
@@ -595,6 +614,9 @@ def animate_graph(self, i):
595614
if (self.delta < self.epsilon * (1 - self.gamma) / self.gamma) or (self.iterations > 60) and self.terminated == False:
596615
self.terminated = True
597616
display(self.grid_to_show, self._height, self._width)
617+
618+
pi = best_policy(self.sequential_decision_environment, value_iteration(self.sequential_decision_environment, .01))
619+
display_best_policy(self.sequential_decision_environment.to_arrows(pi), self._height, self._width)
598620

599621
ax = fig.gca()
600622
ax.xaxis.set_major_locator(MaxNLocator(integer=True))

0 commit comments

Comments
 (0)