-
I noticed a double discounting in both the REINFORCE algorithm and VPG that is not in the original REINFORCE/VPG papers:
```
def optimize_model(self):
T = len(self.rewards)
discounts = n…
-
Now, the VPG model has ActorCriticPolicy for actor (policy) and critic (value function).
It's good to separate them for the separation of concerns and easy to extend policy and value functions in the…
-
1. we need to know the max number of ingredients.
2. plot a histogram of pizzas according to their number of ingredients
3. plot a histogram of teams according to the number of people
4. plot a his…
-
Dear Xu,
This project does not work, there are many bugs and issues, I have tried to reproduce your work for 3 months now, I am not able to get your results. I hope you can reproduce and share the …
-
Using the `--learning-algorithm` CLI parameter if the name is not either `vpg` or `dql` the training will say it is starting but will silently fail.
Reference: https://docs.spiceai.org/deep-learnin…
-
Добрый день.
Не понимаю как использовать библиотеку на длинных запросах,
пример лога
url: 'http://default@localhost:8123/?session_timeout=0&output_format_json_quote_64bit_integers=0&enable_http…
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. Install deepchem latest version in colab `pip install --pre deepchem`
2. Run the following code sample:
```
import deepchem as …
-
As soon as add "AWS::EC2::VPCGatewayAttachment", I got exception, with "KeyError: u'InternetGatewayId'"
```
"DEVLAB1DCGateway": {
"Type": "AWS::EC2::VPNGateway",
"Properties": {
…
-
When I ran `python run_scripts/vpg_run.py`, I had this problem: `ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject`.
Cou…
-
In the VPG implementation, the value loss is calculated,
`value_loss = value_error.pow(2).mul(0.5).mean()`
Isn't the value loss simply the MSE, so just `value_error.pow(2).mean()`? Why the addit…