Yiqi Wang

Hi, First of all, thanks for sharing the code publicly. In the paper, it says your guys are using triplet ranking loss but in the code it is contrastive loss....

[TYPO --> BUGS??] dataset_generator.py get task descriptions wrong?

1

Hi, in the file [dataset_generator.py](https://github.com/stepjam/RLBench/blob/master/tools/dataset_generator.py) , line 246, it has `obs, descriptions = task_env.reset()` to retrieve text descriptions. However, in [task_environment.py](https://github.com/stepjam/RLBench/blob/master/rlbench/task_environment.py) line 89 of reset(), it returns the following: `return...

Hi, I guess the "'pull each end of the rope until **is** is straight'" should be "'pull each end of the rope until **it** is straight'" ? the file[ link](https://github.com/stepjam/RLBench/blob/master/rlbench/tasks/straighten_rope.py)...

VQ-VAE VQ-loss is missing? only find reconstruct, and commitment loss

1

Hi, I am currently studying the VideoGPT and have some doubts on VQ-VAE losses. Where is VQ loss? - In the original [paper](https://arxiv.org/pdf/1711.00937.pdf), there're 3 loss, a reconstruction loss, a...