-
I noticed that the fill_replay function in your code always selects the first description.
```
desc = descs[0]
```
But an RLBench task usually has several different descriptions.
Can the trained …
-
Do you consider the different variants in your training? Does the training set include all the variants? Or did you save some of it for the test set? And the scene coordinate range question, also hope…
-
Hi [@imankgoyal](https://github.com/imankgoyal), thanks for your great work.
While reviewing the code in `rvt/mvt/renderer.py`, I noticed in the `get_cube_R_T` function that the up direction for th…
-
thanks for your great work!!
also i have some questions below:
1、 I want to use the 3d Diffuser actor on an actual robotic arm, but I'm not clear enough on how to collect real data. Can you provid…
-
Hi there, I am running the evaluation through `bash online_evaluation/eval_single_task_mandoo.sh`. However, I met an AttributeError as shown below:
![image](https://github.com/zhouxian/act3d-chained-…
-
I found that `low_dim_state` is used in PerAct. How much impact will this have on the experimental results?
In `peract/agents/peract_bc/launch_utils.py`
QAttentionPerActBCAgent `include_low_dim_…
-
I tried to replicate the experiments in your paper using RLbench.
I created a new task environment in RLbench and attempted to drive it using VoxPoser.
The planner successfully computed waypoints, b…
-
Hi ,
Thank your for release the model.
Does the model control Franka robot in Isaac-sim?
-
Hi, thanks for your splendid work!
I have some questions regarding some implementation details.
1. I would like to implement peract at other datasets, but it requires to extract the key-frame acti…
-
Hi @imankgoyal
Firstly, I would like to express my gratitude for your exceptional work. It's truly inspiring and helpful.
I have a question related to data handling, specifically regarding keyf…