Adrián Javaloy

Results 9 issues of Adrián Javaloy

This pull request adds more reinforcement learning functionality to dlib. Namely it implements the Qlearning and SARSA algorithms. I think I've done a good job with respect to backward compability...

enhancement

Hi! I just found torchtyping a few days ago, and I am enjoying it so far. However, I am a bit confused when it comes to one particular use-case: checking...

**Problem:** RotoGrad accepts as `latent_size` argument a single integer, as the assumption is that gradients are of the form `batch_size x latent_size`. However, some architectures have different shapes for their...

enhancement

Hi, thanks a lot for the plugin! I've been trying to integrate it into my workflow, where I have a folder for Daily Tasks, and then other folders with all...

Hi @pierreablin, Updating the code of [RotoGrad](https://github.com/adrianjav/rotograd), I started using your library, and during testing I've found that the rotation matrices occasionally end up with nan parameters. Debugging the code,...

This is an implementation of #53, in which I add support to provide an adjacency matrix to the autoregressive models, instead of using the ordering between variables. I have added...

### Description I would like to enable support for autoregressive models (that is, MAF, NSF, and NAF) to use a specific adjacency matrix (rather than an ordering), which could be...

enhancement

### Description Now that I am revisiting my experience with Zuko, I have remembered that we did not use NAF in [our work](https://arxiv.org/abs/2306.05415) since, during testing, we highly suspected that...

bug

### ⚠️ Please check that this feature request hasn't been suggested before. - [X] I searched previous [Issues](https://github.com/ivan-lednev/obsidian-day-planner/issues?q=is%3Aissue+is%3Aopen) didn't find any similar feature requests. - [X] I am only requesting...

enhancement