-
Thank you for your outstanding work!
I'm also running my experiments in an RLBench environment, and I have a question for you: Do you know what the three-dimensional position range of the grriper is?…
-
Hi! Thank you for your great works!
I downloaded and decompressed the data and replay, when I executed the training script `python tools/train.py agent=vihe` , after running an epoch I encountered…
-
I'm encountering an issue where the loss values become negative during distributed training. This behavior makes it difficult to determine which checkpoint to use for the final model. Additionally, it…
-
Hello!
Your work looks great!
When I run the eval.py file with reference to readme.md, I get an error:
```
"/home/zqy/code/robotics/RVT/rvt/libs/YARR/yarr/utils/rollout_generator.py", line 40, i…
-
Hi,
Thank you for your wonderful implementation.
When I evaluate task 'open_fridge', I notice that even after calling the [reset_to_demo](https://github.com/stepjam/RLBench/blob/master/rlbench…
-
Hello, I am currently exploring your fascinating project and I have noticed that the relative_action parameter is specifically utilized with CALVIN. I am curious to understand the rationale behind thi…
-
Hi,
It seems that your fork of the rlbench repository does not exist at the moment. As I am interested in reproducing this project, could you please make the repositories available again? Alternative…
-
## My environment
- OS: Ubuntu 23.04
- GPU: RTX 3090
- Copplelia: CoppeliaSim_Edu_V4_1_0_Ubuntu20_04
- Python: 3.11.4
```
Package Version
---------------------- -------
antlr4-p…
-
I am getting errors like this during eval:
> open_drawer 14 0 Expected the action shape to be: (1,), but was shape: (2,)
My train script:
```
main_dir='/path/omitted/'
dataset=/path/o…
-
Octo's action space comprises end-effector velocities, representing changes in ['x', 'y', 'z', 'yaw', 'pitch', 'roll', 'grasp']. I intend to assess the model's zero-shot capability in a simulator. Des…
zwbx updated
7 months ago