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

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

The dqn_agent.py loss function is the wrong way around
Closed 4 months ago1
DQN implementation error
Updated 10 months ago
No gradient required for q_target calculation
Updated 2 years ago
what if i set load_check point to true from argparser
Updated 2 years ago
Network is not learning when convolutional layers are applied.
Updated 3 years ago2
No registered env with id: PongNoFrameskip-v4
Updated 3 years ago2
ndarray error
Updated 3 years ago
Indention of DQN/preprocess_pseudocode is broken
Updated 4 years ago
Detach target nexwork in DQN
Updated 4 years ago
Regarding target calculations in DuelDDQN and indices
Updated 4 years ago
Viewing results of gameplay?
Closed 4 years ago3
Warning: indexing with dtype torch.uint8 is now deprecated, please use a dtype torch.bool instead.
Updated 4 years ago
IndexError: tensors used as indices must be long, byte or bool tensors
Closed 4 years ago5
Runtime error in cartpole_naive_dqn.py
Updated 4 years ago1