Deep-Q-Learning-Paper-To-Code

Deep-Q-Learning-Paper-To-Code copied to clipboard

Hi @philtabor, There is a possible bug in the dqn_agent.py file at line 93: ``` q_target = rewards + self.gamma*q_next ``` needs to be replaced with: ``` with torch.no_grad(): q_target...

Kaustubh-Khedkar

If i set the value of load_checkpoint to True from argparser, how would the if statement work in line 95 of main.py? if not args.load_checkpoint: agent.store_transition(observation, action, reward, observation_, int(done))...

ghost

Network is not learning when convolutional layers are applied.

2

Hey Phil! Thanks for the course. I'm really enjoying it so far. I've implemented the first real Deep Q Network, and it is not learning. Whenever I take off the...

DBaller

No registered env with id: PongNoFrameskip-v4

2

Please, I have the following issue while trying to run main_dueling_ddqn.py 

Elmahedi

I get this error without any line of code with Python 3.8 and the latest pytorch :5: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of...

evo11x

Was a bit confused while testing as the performance was really bad until it hit me that actions are being picked randomly! This should help others I hope.

suryadheeshjith

The indention of DQN/preprocess_pseudocode is broken and difficult to read.

lexxxel

In DQNAgent, I think you may need to call `detach()` at line 90 to detach the target network from gradient evaluation.

yangyi0318

Hi Phil, I implemented your DuelDDQN architecture for myself, and was curious as to the following snippet of the learning function, as my question wasn't detailed in the course. ```...

EXJUSTICE

Update ddqn_agent.py to prevent RuntimeError with newer pytorch version

2

When running the ddqn agent on pytorch v 1.5.0 I get the following RuntimeError: RuntimeError: range.second - range.first == t.size() INTERNAL ASSERT FAILED at ..\torch\csrc\autograd\generated\Functions.cpp:57, please report a bug to...

atlevesque