-
Hi Jingweiz,
this a great implementation of the `DNC`, thanks a lot for sharing it. I was wondering what's the recommended/simplest way to add new environments, (from `OpenAI`)? I guess it would ju…
ghost updated
7 years ago
-
Consider the case where there are only a few states that an MDP can transition to given the current state (e.g. GridWorld). This is quite common, and it would be very useful for beginners (e.g. AA228 …
-
Hi,
I am trying to run the tests by running under the src folder:
`python -m unittest discover`
but I receive the following error:
```
==================================================…
-
I receive the following error when trying to train on the 28x28 gridworld dataset:
```cPickle.UnpicklingError: BINUNICODE pickle has negative byte count```
I have tried re-downloading (which did…
-
I'm getting this strange error running the reinforce-gridworld notebook.
But not another machine with almost the same conda installation run without problem!
Any guess?
Thank you
Marco
----…
-
I cannot understand what the label in the dataset is for. Could you please elaborate a little bit? Thanks.
-
I try to clone and run it on my computer but I got this error:
Traceback (most recent call last):
File "experiments.py", line 178, in
experiment_overlapping(name = "overlapping",steps =15,i…
-
Hello, it's a great work. But where is ./models/download_models.sh ?
-
### Sumario
Inspirado en ideas de la psicología cognitiva, el *reinforcement learning* ha permitido generar algoritmos que aprenden de la experiencia cruda. Haciendo uso de estos métodos hemos logr…
-
In the GridWorld.py, you write the code using bellman equation to update the value function:
```Python
while True:
# keep iteration until convergence
newWorld = np.zeros((WORLD_SIZE, WORLD…