packtpublishing / hands-on-reinforcement-learning-with-python Goto Github PK

I'm actually reading the 3rd chapter when we try to implement a way to resolve the fronzenlake environnement,

As it is written : "We give +1 point as a reward to the agent if it correctly walks on the frozen lake and 0 points if it falls into the hole"

So my question is, why would the agent want to reach the exit of the Lake if the environnement is not giving him negative reward for each step past on the Lake ?

I thought the agent would want to maximize his rewards by walking infinitely on frozen place which gives him +1 reward.

Thx in advance

PkgResourcesDeprecationWarning: Parameters to load are deprecated. Call .resolve and .require separately.
result = entry_point.load(False)

Hello! I'm reading a book now.

I try to run the tasks that are given in the second chapter. The task where the robot learns to walk turned out to run, it works.

But when launching a program with a bot for the video game "Auto-Racing", an error occurs:

KeyError: 'flashgames.NeonRace-v0'

During handling of the above exception, another exception occurred:

UnregisteredEnv Traceback (most recent call last)
in
3 import random
4
----> 5 env = gym.make('flashgames.NeonRace-v0')
6 env.configure(remotes = 1) # автоматически создает локальный контейнер docker
7 observation_n = env.reset()

/opt/anaconda3/envs/universe/lib/python3.6/site-packages/gym/envs/registration.py in make(id, **kwargs)
140
141 def make(id, **kwargs):
--> 142 return registry.make(id, **kwargs)
143
144 def spec(id):

/opt/anaconda3/envs/universe/lib/python3.6/site-packages/gym/envs/registration.py in make(self, path, **kwargs)
84 else:
85 logger.info('Making new env: %s', path)
---> 86 spec = self.spec(path)
87 env = spec.make(**kwargs)
88 # We used to have people override _reset/_step rather than

/opt/anaconda3/envs/universe/lib/python3.6/site-packages/gym/envs/registration.py in spec(self, path)
126 raise error.DeprecatedEnv('Env {} not found (valid versions include {})'.format(id, matching_envs))
127 else:
--> 128 raise error.UnregisteredEnv('No registered env with id: {}'.format(id))
129
130 def register(self, id, **kwargs):

UnregisteredEnv: No registered env with id: flashgames.NeonRace-v0

When installing, I had a problem related to mujoco-py. Could the fact that the program does not start be related to this?
Installed OpenAi on a macbook with MacOS Catalina ver. 10.15.2.
I will be grateful for the help.