Arjun Narayanan
Arjun Narayanan
Right now `PeriodicBC` assumes that the end-points of a discretization do not overlap under periodicity. To make this work, the user must be aware of this assumption and ensure that...
I think we need to pass `traj[:terminal]` to `discount_rewards` so that the gain is computed only up to termination of an episode? https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/6fe6aa01208c325f8f990032621c18b61d574b37/src/ReinforcementLearningZoo/src/algorithms/policy_gradient/vpg.jl#L105
**Describe the bug** The `ViTAutoEnc` constructor hard-codes the output patch size to 4 in [this line](https://github.com/Project-MONAI/MONAI/blob/ae95bf920daad142bd8230580617a5e0a8d5d907/monai/networks/nets/vitautoenc.py#L103). [Edit] I think `new_patch_size` needs to be equal to `patch_size` In particular, this results...
Is there a way to determine all the neighbors of a given leaf? If this requires a pull request I am happy to try and look into it :)