-
https://github.com/pytorch/rl/blob/3595c45eeb0c3e45c41bfff99ecbc973a7d1704f/torchrl/objectives/ddpg.py#L272
this line is not compatible with multi-agent, as it unsuquezees a dimension before the ag…
-
I really like `stable_baselines` and would like to use it for a custom environment with continuous actions. To match the specific needs of the environment, I need to apply a custom activation function…
-
Although I tried to replace the trace generator with one that can load directly load .swf files, the simulation step is extremely slow and unable to be used to train RL agents.
-
Is laser_tag not available for this game? When I run example --game=laser_tag, the following message appears:
Creating game..
Starting new game...
Initial state:
State:
.......
.......
..*.*.…
-
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
BC algorithm can fall victim to covari…
-
Hi Lucas,
First, I really like the Python library you and your team have put together. I currently use this library for my PhD research concerning collaborative multi-agent algorithms.
My quer…
-
When I try to run the mentioned code to generate a cache of stable grasps for different cube sizes:
```
for cube_scale in 0.9 0.95 1.0 1.05 1.1
do
bash scripts/gen_grasp.sh $cube_scale custom_gr…
-
# Tak
Tak is an abstract strategy board game similar to Go, except pieces can stack on top of each other into the third dimension. There is an active community that plays this game, makes bots and …
-
Hello, ML agents developer! I'm very happy to use your training tools,but I have some problems in using them at present.
I'm trying to use [Python-API.md](https://github.com/Unity-Technologies/ml-a…
-
Some specification on performance benchmarks:
- run the benchmarks on CPU and GPU
- Profiling to find bottleneck (if any)
- Metrics for comparison: timesteps / unit time, updates / unit time
- vary …