-
### Scenario trees/lattice reading
Scenarios for multistage stochastic programs
https://www.karlin.mff.cuni.cz/~kopa/papers/vanc-ed.pdf
Overview of scenario tree generation methods, applied in …
msz13 updated
2 weeks ago
-
## 🚀 Feature
I would like to suggest new stochastic optimizer additions to Pytorch.
### For non-convex loss functions
It is known that adaptive stochastic optimizers like Adam, Adagrad, RMSprop c…
-
### Description
I sometimes, but not consistently, get the following jaxlib.xla_extension.XlaRuntimeError when training a neural network with sine activations in JAX on an NVIDIA A100 GPU:
```
jax…
-
Reported by: prckent
Ye Luo reports odd behavior of stochastic reconfiguration DMC after equilibration suggesting it is not correct. Stochastic reconfiguration is highly desirable when running on lar…
-
The stochastic simulation algorithms should all accept a seed for the random number generator to ensure reproducibility.
-
There are many algorithms in the book haven't a written pseudocode (stochastic hill climbing - local beam and its variants - ... ) . It would be beneficial, if they are to be implemented I guess ... s…
-
I would like to suggest adding Optimization functions, machine learning and deep learning algorithms in this repository. This can be added in a separate folder called `machine_learning` folder. Furthe…
-
## Motivation
This will be useful for people implementing stochastic algorithms and want the script to respect pytorch seed. np also has this.
cc @mruberry @rgommers
-
The stochastic algorithms is OK, but for some difficult problems it takes a good while to find the solution. Another option with a elitist algorithm would be much better.
-
I know that the library is aimed at RL-based planners. Is there any plan to support forward simulation that allows us to implement A*-based and MCTS planners? There is this project called [plangym](ht…