ryanmaxwell96
ryanmaxwell96
Was there any resolution to this issue? I've tried the same suggestions that have been listed so far (os.environ['OPENAI_LOGDIR'] = ... and os.environ['OPENAI_LOG_FORMAT] = 'stdout,tensorboard') and I can get those...
I am also getting the same issue with 0.15.4. Any help?
So I'm not sure if this is the answer, but upon looking into the gym/gym/wrappers, folder, it looks like there are only files named "flatten_ovservation" and "filter_observation" so I just...
So what if we have 0.15.4 already? go even earlier?
I was finally able to get it to work, though with gym 0.15.3 not 0.15.4. Also, I had to remove two underscores in the run.py.
Also, can you help me understand why there are multiple neural network outputs? I tested the halfcheetah code and found out that the observation is a (1,27) but for some...
Unless it refers to the 6 half-cheetah joints that can move depending on the state (of 27 dimensions). So depending on which of these states it is in, the policy...
Ok thank you. Sorry I have another question. Where is the name "policy_nn" coming from? I'm guessing it is the last layer, correct?
Can you please explain to me why in value.py it has an output Dense layer of size 1? Shouldn't it be the same size as the action dimension?
Also, how do you use plotting.py? I don't see it currently being used in any of the code.