-
### What is the problem?
In a `TorchPolicy` (I did not test with `TFPolicy`) with `LearningRateSchedule` mixin, the lr value of the optimizers lr_group are not updated (LR stays constant). The `cur_l…
-
I've been trying to set up a basic DQN agent to learn the OpenAI Taxi Environment. I've been trying with a simple network with just an embedding layer which is basically a Q table, but it only seems t…
-
- need to actually create a tensorflow NN implementation (or two) to interact with the gym
-
### What is the problem?
I saved a checkpoint from a `PPOTrainer` for the Bipedal Walker gym environment, using Ray 0.8.5. I attempted to restore it later using the same code, but Ray 0.8.6. Th…
-
Dear Developers,
I didn't receive answer on ray-dev@ for two weeks, so let's see here :)
I am curious if the DQN / Rainbow implementation can be run with either TF or Pytorch backend? I couldn't…
-
## 📚 Documentation
Hello,
There are broken links in `README.md` on [Dueling-DQN and Reinforce](https://github.com/PyTorchLightning/pytorch-lightning/blame/9c415d2c71ddc44ca3344ba1136c0dd546fc5ef6…
-
Hello,
Loving the book, but in Ch. 8 receive this error for all scripts:
Traceback (most recent call last):
File "C:/Users/hj/PycharmProjects/DeepLearning/01_dqn_basic.py", line 62, in
comm…
-
### trainer automatically dies after certain time?
*Ray version (0.8.5), and other system information (Python version(3.6.0), Pytorch version, Ubuntu - 16.04):*
```
(pid=26955) *** Aborted at…
-
Hi there!
We're 5th semester bachelor students and would like to use your performance metrics in analyzing different versions of our DQN implementation for the LunarLander-V2 gym. Unfortunately, we…
-