vmayoral / basic_reinforcement_learning Goto Github PK

I'm getting lots of errors when I try to run the code for tutorial 1. Kindly advise.

Screen dump:
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python3 egoMouseLook.py
File "egoMouseLook.py", line 162
print len(mouse.ai.q) # print the amount of state/action, reward
^
SyntaxError: invalid syntax
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ nano egoMouseLook.py
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python3 egoMouseLook.py
Traceback (most recent call last):
File "egoMouseLook.py", line 7, in
import cellular
File "/home/administrator/basic_reinforcement_learning/tutorial1/cellular.py", line 521
print 'Error: invalid colour:', c
^
SyntaxError: Missing parentheses in call to 'print'. Did you mean print('Error: invalid colour:', c)?
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python egoMouseLook.py
Traceback (most recent call last):
File "egoMouseLook.py", line 7, in
import cellular
File "/home/administrator/basic_reinforcement_learning/tutorial1/cellular.py", line 521
print 'Error: invalid colour:', c
^
SyntaxError: Missing parentheses in call to 'print'. Did you mean print('Error: invalid colour:', c)?
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ nano cellular.py
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python egoMouseLook.py
Traceback (most recent call last):
File "egoMouseLook.py", line 8, in
reload(cellular)
NameError: name 'reload' is not defined
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python3 egoMouseLook.py
Traceback (most recent call last):
File "egoMouseLook.py", line 8, in
reload(cellular)
NameError: name 'reload' is not defined
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ cd ..
(base) administrator@ubuntu:/basic_reinforcement_learning$ python tutorial1/egoMouseLook.py
Traceback (most recent call last):
File "tutorial1/egoMouseLook.py", line 8, in
reload(cellular)
NameError: name 'reload' is not defined
(base) administrator@ubuntu:/basic_reinforcement_learning$ cd tutorial1
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ nano egoMouseLook.py
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python3 egoMouseLook.py
Traceback (most recent call last):
File "egoMouseLook.py", line 133, in
world = cellular.World(Cell, directions=directions, filename='../worlds/waco.txt')
File "/home/administrator/basic_reinforcement_learning/tutorial1/cellular.py", line 102, in init
data = file(filename).readlines()
NameError: name 'file' is not defined
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ nano egoMouseLook.py
(base) administrator@ubuntu:/basic_reinforcement_learning/tutorial1$ python3 egoMouseLook.py
egoMouseLook.py:9: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
import imp
Traceback (most recent call last):
File "egoMouseLook.py", line 134, in
world = cellular.World(Cell, directions=directions, filename='../worlds/waco.txt')
File "/home/administrator/basic_reinforcement_learning/tutorial1/cellular.py", line 102, in init
data = file(filename).readlines()
NameError: name 'file' is not defined

In tutorial1, qlearn_mod_random.pyline 32:

if random.random() < self.epsilon:
            minQ = min(q)
            mag = max(abs(minQ), abs(maxQ))
            # add random values to all the actions, recalculate maxQ
            q = [q[i] + random.random() * mag - .5 * mag for i in range(len(self.actions))]
            maxQ = max(q)

why use this(versus qlearn.py)?

Error

1. openai_gym_4.py

       env.monitor.start('/tmp/cartpole-experiment-1',force=True)
       AttributeError: 'TimeLimit' object has no attribute 'monitor'

2. openai_gym_5.py

       gym.upload('/tmp/cartpole-experiment-1', api_key='sk_5YJsWfHOQwOLiU3AAVyYeA')
       AttributeError: module 'gym' has no attribute 'upload'