R docs on R^2 incorrectly say that it's not supported for non-linear models

[exalate-issue-sync]

Even though we shouldn’t report R^2 for non-linear models (see [https://h2oai.atlassian.net/browse/PUBDEV-5381|https://h2oai.atlassian.net/browse/PUBDEV-5381|smart-link] ), we do. So the R docs for {{h2o.r2()}} are incorrect in saying that it returns NaN for non-linear models. This might be in Python too. Let's delete this.

It says:
Retrieves the R2 value from an H2O model. Will return R^2 for GLM Models and will return NaN otherwise. If "train", "valid", and "xval" parameters are FALSE (default), then the training R2 value is returned. If more than one parameter is set to TRUE, then a named vector of R2s are returned, where the names are "train", "valid" or "xval".

[h2o-ops]

JIRA Issue Details

Jira Issue: PUBDEV-8744
Assignee: hannah.tillman
Reporter: Erin LeDell
State: Resolved
Fix Version: 3.36.1.3
Attachments: N/A
Development PRs: Available

[h2o-ops]

Linked PRs from JIRA

#6229