-
Importance-Sampling(IS) Weights
-
Hi there! First off, thank you so much for making this software available to the public. I am getting an error when running the tutorial data. I've tried it on a server and local system so I'm not sur…
-
I noticed while browsing the RL examples that the PPO implementation is actually A2C (which there's already an example for). On line 141, this line:
```Rust
let action_loss = (-advantages.detach()…
-
I have a model that I compile with
```
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[matthews_correlation])
```
and it fails after the first epoch
```
17/18 [==========…
-
Learn L (number of intervals) and each quantile point of unknown distribution function F.
## [code](https://colab.research.google.com/drive/1BwXO_MlslMqY4wBHrXppAb42BBP37r8H?usp=sharing)
## ref
[Qu…
-
Currently sandwiched with sampling priorisation in this PR:
https://github.com/GEO-BON/bon-in-a-box-pipelines/pull/99
We should make a separate pipeline for BRT, test and merge it.
-
Tail approximation with importance sampling (and possibly also saddlepoint approximation) gives wrong results with un-normalized foreground and/or backgrounds.
-
Looks like the `lnlike` function in `importance_sampling.py` could be refactored to call out to one of any number (currently two) model's likelihoods. Let's do this refactoring so that we can explore …
-
### Description
For offline rl it would be really useful to have the fqe direct and doubly robust methods be updated for continuous action spaces also, not just discrete action spaces.
### Use cas…
-
Support for additional OPE algorithms such as weighted importance sampling, doubly robust.