gflownet
gflownet copied to clipboard
alexhernandezgarcia
Generative Flow Networks - GFlowNet
- Puts all tensors into the device change: https://github.com/alexhernandezgarcia/gflownet/blob/bcb14436b45fe54373a72b84b0f5f1f9ef81128e/gflownet/envs/grid.py#L181 To: ``` cols = states + torch.arange(self.n_dim, device=self.device) * self.length ```
Currently, the actions are [converted into tensors in the Batch](https://github.com/alexhernandezgarcia/gflownet/blob/main/gflownet/utils/batch.py#L477). It seems that it is not necessary and it leads to inefficiency, for example [in the computation of log probabilities](https://github.com/alexhernandezgarcia/gflownet/blob/main/gflownet/envs/base.py#L547).
currently, `self.env` is stored in the GFlowNet class, because other classes expect an env instance (to access various methods / attributes). Since the gflownet now stores a class factory rather...
Thanks for the lovely work! Are there any example scripts for generating conformational ensembles for proteins similar to what is done in the paper [Towards equilibrium molecular conformation generation with...
* [x] remove test logic from main `GFlowNetAgent` * [x] rename to `eval()` logic to be semantically distinct from (unit, integration etc.)-tests * [x] clean up evaluation return values (to...
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 outputs and reward....
- Policies were originally MLPs. - Now we need to be able to use arbitrary function approximators. - This will be a library-level change that will affect all projects.