-
Dear Leonardo Albuquerque
Could you specify in the README file of how to run your code?
-
Saw this and it sounded cool. Are you able to please tell me more?
-
In RL algorithms, it is every common to compute return-like things from trajectories. It is inefficient to compute such returns with normal python for-loops. In order to improve efficiency, we'd bette…
-
Hi @ChanganVR,
I am using habitat v0.1.7 and when I run `python ss_baselines/av_nav/run.py --exp-config ss_baselines/av_nav/config/audionav/replica/train_telephone/audiogoal_depth.yaml --model-dir …
-
For example, if we ask the model to generate a program, rather than simply continuation.
If we do not fine-tune them, RL does not even know what to generate I believe.
Do you have more thoughts …
-
The `ppobyter/events/timedevent.py` class and all classes that inherit from it should be replaced with normal events, and the scheduling of this should happen server side. This should be sent to all …
-
here is my full error at first when `wandb login`
```
Traceback (most recent call last):
File "/home/yhn/.conda/envs/yh/bin/wandb", line 8, in
sys.exit(cli())
File "/home/yhn/.conda/en…
-
Could someone please help me? I am training my PPO model with 128 parallel environments and at the step number 2340992 comes this error that stops the execution of the script. I tried to reduce the nu…
-
Hi @MillionIntegrals. I was wondering, is the default model used by vel recurrent? If not, is there an example with a recurrent model.
I'm trying to train something on the `MiniWorld-MazeS2-v0` env…
-
A3C: aka Asynchronous Advantage Actor Critic
It uses MPI, so I wonder if DeepMimic be trained using A3C?