David Foster

Masking illegal actions

2

Is there any interface for masking illegal actions? Ideally, I'd like the agent network to only apply the softmax over the set of legal moves (which can be calculated as...

Monotonic constraints

3

An extremely useful feature of some gradient boosting libraries is the ability to enforce monotonic constraints - e.g. https://xgboost.readthedocs.io/en/latest/tutorials/monotonic.html Are there plans to get this implemented within NGBoost? Thanks, David

[question] EvalCallback using MPI

5

When running a training loop using MPI, the `EvalCallback` doesn't seem to make use of the parallelisation: for example, in this `train` function: https://github.com/hardmaru/slimevolleygym/blob/master/training_scripts/train_ppo_mpi.py it seems that the `EvalCallback` will...

`infer_deployment` function broken

6

- **Package Name**: azureml-rag[faiss,document_parsing,cognitive_search,hugging_face] - **Package Version**: 0.2.2 - **Operating System**: Linux - **Python Version**: 3.10 **Describe the bug** A clear and concise description of what the bug is. The...

Multipage apps

3

Great library - thanks! How would you use this to log the user in once at the start of a session and remember the fact that the user is logged...