I m trying to perform reinforcement learning algorithms on the gridworld environment but i can't find a way to load it.
I have successfully installed gym and gridworld 0.14.0 then I executed this command
env = gym.make("gridworld-v0")
I then obtained the following error stack
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
~/anaconda3/lib/python3.7/site-packages/gym/envs/registration.py in spec(self, path)
131 try:
--> 132 return self.env_specs[id]
133 except KeyError:
KeyError: 'gridworld-v0'
During handling of the above exception, another exception occurred:
UnregisteredEnv Traceback (most recent call last)
<ipython-input-36-b3991c5b334f> in <module>
----> 1 env = gym.make("gridworld-v0")
2 env.setPlan("gridworldPlans/plan1.txt", {0: -0.001, 3: 1, 4: 1, 5: -1, 6: -1})
3 statedic, mdp = env.getMDP()
~/anaconda3/lib/python3.7/site-packages/gym/envs/registration.py in make(id, **kwargs)
154
155 def make(id, **kwargs):
--> 156 return registry.make(id, **kwargs)
157
158 def spec(id):
~/anaconda3/lib/python3.7/site-packages/gym/envs/registration.py in make(self, path, **kwargs)
98 else:
99 logger.info('Making new env: %s', path)
--> 100 spec = self.spec(path)
101 env = spec.make(**kwargs)
102 # We used to have people override _reset/_step rather than
~/anaconda3/lib/python3.7/site-packages/gym/envs/registration.py in spec(self, path)
140 raise error.DeprecatedEnv('Env {} not found (valid versions include {})'.format(id, matching_envs))
141 else:
--> 142 raise error.UnregisteredEnv('No registered env with id: {}'.format(id))
143
144 def register(self, id, **kwargs):
UnregisteredEnv: No registered env with id: gridworld-v0
I d expect it to be enough to load the environment but it is apparently enough.
Could you please advice me on how to proceed?
Cheers, Paul
Should be in Caps:
env = gym.make('Gridworld-v0')
Further reference: https://pypi.org/project/gym-gridworlds/