rl_a3c_pytorch

rl_a3c_pytorch copied to clipboard

Need a model, thank you

1

SpaceInvaders-v0，please

abolaer

Is it normal to get this trace back in the console? It spams for a few dozen times and then stops abruptly. Then, it starts logging the training session as...

josh-tegus

added trained model for MsPacman-v0

3

Trained MsPacman model for 2 days. Averaging 6.7k score per 100 epochs, high score ~ 10.5k

enochkan

question about trained models

1

Just want to clarify that there is only one saved model per environment and it will be overwritten each training epoch, right? For example, MsPacman will only have one saved...

enochkan

Need for trained models

2

Hi, Due to lack of resources, i cant train the models myself. Therefore, I need the pre trained models of the various games. Is it possible for you to share...

pulkitso

Is there any necessary to lock when update params?

1

It seems doesn't get lock when update network params in SharedAdam. However, isn't there process safety problem without a lock?

Ranglage

Question about Test function

1

Hi, I'd to have a question about the following block https://github.com/dgriff777/rl_a3c_pytorch/blob/eb5c9b909abc02911b45e325f7a7c619d3b0fa46/test.py#L60 ``` if player.done and not player.info: state = player.env.reset() player.eps_len += 2 player.state = torch.from_numpy(state).float() if gpu_id >= 0:...

AlexTo

Cannot import test

1

gitjeet

Stuck when training in MsPacman-v0

7

Hi @dgriff777 . Thank you for your repo. It's great that it can achieve such a high score. But I met a problem when I try to apply it to...

KarlXing

eps for Adam

2

Is there a reason why the default for eps in the adam optimizer is so high? Currently, it is 1e-3 [line 104 in shared_optim.py]. Usually, it's around 1e-08. Just wanted...

jsuit