-
Hi, I'm a college student studying reinforcement learning.
I want to learn how to create an expert model (pkl) and run my code in a new environment.
Now, I tried to create a model using torchR…
-
Hi there,
I'm very interested in using your benchmark. It may be of interest to include the Kuramoto-Sivashinsky equation in the benchmark? You can find an implementation (albeit in the torchrl lib…
-
Command: `HYDRA_FULL_ERROR=1 sim_backend=MUJOCO MUJOCO_GL=egl python train.py task=kitchen_knob1_off-v3 visual_transform= env_per_collector=1 lr=1e-3 hydra/launcher=local hydra/output=local`
``…
-
## Describe the bug
When training on `PettingZoo/MultiWalker-v9` with `Multi-Agent Soft Actor-Critic`, **all** losses (`loss_actor`, `loss_qvalue`, `loss_alpha`) explode after ~1M environment steps…
-
Hi All
Is it possible to run DMLab2d with vectorised environments? I am using CleanRL + Shimmy to run MeltingPot but when I try to use `concat_vec_envs_v1` I get error: `TypeError: cannot pickle dm…
-
### 🐛 Describe the bug
`lib/python3.10/site-packages/torchrl/data/replay_buffers/samplers.py:23`:` UserWarning`: Failed to import torchrl C++ binaries. Some modules (eg, prioritized replay buffers) m…
-
Hello, recently I want to try Omnidrones in my project. But I met some problems. I want to use the Omnidrones program based on the isaac sim2022.2.0 version, but the latest versions of torchrl and ten…
-
## Motivation
In the current implementation of the VMAS environment, the done fields are only available on the root of the tensordict. However, for training, it is useful to have them in the group-…
-
When I run `agenthive/examples/train.py ` , there happens a KeyError: 'full_done_spec'
```
/home/dellpc/anaconda3/envs/hive/bin/python /home/dellpc/Downloads/robot/code/hive/agenthive/examples/tra…
-
Hi there,
As mentioned [here](https://github.com/NVIDIA-Omniverse/Orbit/discussions/108#discussion-5511668), I'm trying to use torchrl with [NVIDIA Orbit](https://github.com/NVIDIA-Omniverse/Orbit)…