-
### What is the problem?
rllib is not using the GPUs at all during training, leaving the CPUs completely overwhelemd. torch returned from try_import_torch() returns true when calling torch.cuda.i…
-
When I set `num_workers=1` or other value greater than 0 in `torch.utils.data.DataLoader`, I get this error.
The detail of the error:
```
Traceback (most recent call last):
File "/opt/project/t…
-
After clicking create project for UE5 (previously it would allow project creation for other versions, and the free plugin was also available for other versions, but now it shows support for only UE5 o…
-
### 🐛 Bug
when i vec the env by `make_vec_env(MyWrapper, n_envs=16` then comes error behind.
but when i vec the env by `DummyVecEnv([MyWrapper] * 16)` everything goes well.
### To Reproduce
```…
-
Hi, I am trying to create a good Ai for the backgammon game, as there are no examples for it. I tried pure PPO, but it did not give very good results. I was thinking to apply the AlphaZero algorithm, …
-
uhm, i also try to train this based on pytorch dqn tutorial.
But the problem is that it is not stable.Eg: at the episode of 1000, some time it did pretty good, and others were too bad!!!
i see your …
-
### 🐛 Bug
Hello everyone, I appreciate your work. I have a little bit embarrassing problem =|
I have recently encountered an issue while attempting to train, save, and reload my **DQN** model w…
-
I couldn't find a policy-gradient-based historical self-play here in open-spiel where we iteratively build up an archive of past solutions for the agent to train against -- similar to [emergent comple…
-
https://github.com/datawhalechina/easy-rl/blob/master/notebooks/DQN.ipynb
与https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html
基本一致，可以加个参考。
-
Here: https://pytorch-lightning-bolts.readthedocs.io/en/latest/reinforce_learn.html#dqn-results
It should be:
`from pl_bolts.models.rl.dqn_model import DQN`
and not:
`from pl_bolts.models.rl i…