Prasad Chalasani

model.predict() should not require presence of "target"

4

When I try to do `model.predict(df)` and `df` does not contain the target, I get an error. In predict mode, it shouldn't care if the "target" is present or not,...

This is a simplified version of my scenario. Say I have a df with these columns: `groupID, time_idx, x, y`. At any time T, I want to use the values...

- PyTorch-Forecasting version: 0.10.1 - PyTorch version: 1.11.1 - Python version: 3.8.10 - Operating System: MacOS ### Expected behavior My `TimeSeriesDataSet` was created via ``` dataset = TimeSeriesDataSet( df_all, group_ids...

Fix issue #275: training=False needed for eval envs

6

Normalization stats should not be updated during evaluation, e.g. in callbacks such as `EvalCallback`. If they are updated during evaluation, it can lead to unexpected inconsistencies between results produced in...

VecNormalize: training should be set to False for eval environments (?)

3

**Describe the bug** I don't know if this was intentional, but I do not expect normalization stats to be updated in an evaluation environment (either in an EvalCallback or in...

The example below computes quantiles for randomly shuffled numbers in the range 0..1000. The 10% and 90% quantiles don't look good. By contrast the this Java library https://github.com/mayconbordin/streaminer gives reasonably...

Small documentation bug

1

In Aggregation functions section, the explanation of the example says: ``` pyDatalog searches all possible solutions for manager['Mary']==Y, then counts the number of Y. ``` but it should be: ```...

multi-module usage?

1

I've been staring at the "multi-module" usage section and it's not clear at all how to use this plugin for multiple modules?

`ExperimentManager.objective()` should return `best_mean_reward` not `last_mean_reward`

6

https://github.com/DLR-RM/rl-baselines3-zoo/blob/38eb59d74c49eaf77d8994fd28d220a9f65a21ee/utils/exp_manager.py#L727 In case we use early stopping in training (e.g. with `StopTrainOnNoModelImprovement`), the `last_mean_reward` may be bad, so it's best to return `best_mean_reward`

what exactly is the input data format expected by Metronome?

4

subject says it all