-
Algorithms in ```qpolgrad``` have been organized to define functions for loss calculation. Those functions are then called in the ```update``` function for the algorithm. A2C and PPO need to be brough…
-
Importing A2C agent from rlberry.agents.torch automatically tries to import optuna (which is not part of rlberry's install dependencies, but of "default" dependencies which are part of extra dependenc…
-
Hi, i want to use "num_envs" argument. When i command like "PYTHON_PATH scripts/rlgames_train.py task=ShadowHand num_envs=512", i got error message below. How can i use "num_envs" argument?
Thank you…
-
Versions:
uniforms: ^3.10.1
uniforms-mui: ^3.10.1
```
type A1 = {
id_type: 'a1';
id: string;
};
type A2 = {
id_type: 'a2';
id: string;
};
type C = {
name: string;
addres…
-
I haven't found the official code of AD, but there's some new works based on it such as DPT which the authors have released their code. I'm confused if i missed the AD's code. Could you please provide…
-
Thank you for releasing this work! I was trying to run the humanoid example provided in the README, but consistently got this error:
```
Error executing job with overrides: ['task=HumanoidGPT', 'wan…
-
How to do hyper parameter tuning for SB3 algorithm such as PPO, A2C, DQN?
-
When going to flat mode, Piwigo doesn't follow the expected sort orders.
Let's imagine you have defined this manual order (for albums and for photos inside the 3 albums)
```
* album A
** album A2
**…
-
I wrote an A2C have the same problem, is the problem of A2C?
-
执行
`python demo_A2C_PPO.py --gpu=0 --drl=0 --env=6`
出现异常
```
File "elegantrl/train/evaluator.py", line 176, in get_cumulative_rewards_and_steps
tensor_action = tensor_action.argmax(dim=1)
In…