philtabor Deep-Q-Learning-Paper-To-Code issues

philtabor / Deep-Q-Learning-Paper-To-Code

MIT License

340 stars 146 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

The dqn_agent.py loss function is the wrong way around

#19 i1Cps closed 5 months ago
1
DQN implementation error

#18 majid5776 opened 10 months ago
0
Fix for Gym environment framework changes

#17 marginloop opened 1 year ago
0
No gradient required for q_target calculation

#16 Kaustubh-Khedkar opened 2 years ago
0
what if i set load_check point to true from argparser

#15 ghost opened 2 years ago
0
Network is not learning when convolutional layers are applied.

#14 DBaller opened 2 years ago
2
No registered env with id: PongNoFrameskip-v4

#13 Elmahedi opened 2 years ago
2
ndarray error

#12 evo11x opened 3 years ago
0
Updated Epsilon in main_dqn for testing without changing parameter value

#11 suryadheeshjith opened 3 years ago
0
Indention of DQN/preprocess_pseudocode is broken

#10 lexxxel opened 3 years ago
0
Detach target nexwork in DQN

#9 yangyi0318 opened 3 years ago
0
Regarding target calculations in DuelDDQN and indices

#8 EXJUSTICE opened 3 years ago
0
Viewing results of gameplay?

#7 EXJUSTICE closed 3 years ago
3
Fix uint8 issue for newer versions of PyTorch

#6 srikanthkb opened 4 years ago
0
Warning: indexing with dtype torch.uint8 is now deprecated, please use a dtype torch.bool instead.

#5 srikanthkb opened 4 years ago
0
Fix typo, use "rewards" instead of "reward" in cartpole_naive_dqn.py

#4 lydxlx1 closed 4 years ago
0
Update ddqn_agent.py to prevent RuntimeError with newer pytorch version

#3 atlevesque opened 4 years ago
2
IndexError: tensors used as indices must be long, byte or bool tensors

#2 Ningizza closed 4 years ago
5
Runtime error in cartpole_naive_dqn.py

#1 vvrs opened 4 years ago
1