-
Currently, the proxy is set as an attribute of the environments and the base environment implements the methods `proxy2reward()` and `reward2proxy()` that determine the conversion between proxy output…
-
A `CONTRIBUTING.md` will give a clear expectation and starting point for new developers of `gflownet`. I've found that the [tensorflow-addons CONTRIBUTING.md](https://github.com/tensorflow/addons/blob…
-
I've just started with gflownets and wanted to run the code using the default parameter values, however I keep getting exception while sampling, and ultimately, an attribute error with torch_geometric…
-
Hi. I'm trying to train a DiscreteEBM environment for square lattice ising model. It's working fine with small grid lengths but when I attempt to increase the grid length i get this:
`RuntimeError: …
-
Hi!
Thanks for your work on this library, it's much appreciated.
I'm working on a physics project with GFlowNets and was recommended this repo by Bruno Rousseau from MILA.
I've been able to port …
-
The way the common tests are implemented has several issues. Importantly, the repetition decorators are ignored.
See this comment: https://github.com/alexhernandezgarcia/gflownet/pull/204/files#r13…
-
Hi, I generated a dataset then tried to run main.py and am getting Failed to read errors followed by the paths of the graphs. I verified the paths specified exist and point to graph .gpickle files.
…
ghost updated
9 months ago
-
# 🐛 Bug
There is a bug in botorch.utils.multi_objective.pareto.is_non_dominated, where deduplicate is ignored whenever the size of the data is large enough.
## To reproduce
** Code snippet to…
-
any time in a test we use `N`, this should be a test-specific key in a dict from the super class.
-
in `base.py`
```
log_rewards = trajectories.log_rewards
# TODO: log_reward_clip_min isn't defined in base ().
if math.isfinite(self.log_reward_clip_min) and log_rewards i…