Théo VINCENT

It seems like there is a mistake in the target maker. https://github.com/isl-org/DirectFuturePrediction/blob/b4757769f167f1bd7fb1ece5fdc6d874409c68a9/DFP/future_target_maker.py#L69 I guess we should substract the mean of the measurements in stead of the value of the measurement...

It seems that the method *is_valid_transition* of OutOfGraphReplayBuffer is not checking if the stacked images are coming from another __truncated__ trajectory, in which case the index is invalid. It only...

Hi, I am currently working on the paper that you published with this repository. By looking at your Notebooks, I realized that, for the search method `Win`, the results shown...

Hi, I am currently working on the paper that you published with this repository. In the paper, it is said that the cost functions used to build the ensemble methods...

Hi, I am currently working on the paper that you published with this repository. I am trying to add an example of your work in the galery of examples of...

Hi, I am currently working on the paper that you published with this repository. By looking at your code, I realized that you are treating the search methods Win and...

Bug in the Reply Buffer: end of episodes is not correctly handled

1

Hi, Thank you for your great work. It is really cool to open source such an amazing code base! ## TL;DR @yogesh1q2w, and I noticed that the last transitions of...

Hi, Thanks again for the amazing code base! The second and third definitions of the convolution layers are missing the initializer type, while the initializer type is defined earlier. Is...