Added Expectile Regression Naive implementation

[RylanSchaeffer]

Continuing from #9, I made the minor changes Mark and Will recommended, but did not pursue writing expectile_naive_regression_loss() to work with expectile regression since properly implemented expectile regression is more complicated (and I think will require its own PR).

[google-cla]

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

📝 Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here with @googlebot I signed it! and we'll verify it.

---

What to do if you already signed the CLA

Individual signers

• It's possible we don't have your GitHub username or you're using a different email address on your commit. Check your existing CLA data and verify that your email is set on your git commits.

Corporate signers

• Your company has a Point of Contact who decides which employees are authorized to participate. Ask your POC to be added to the group of authorized contributors. If you don't know who your Point of Contact is, direct the Google project maintainer to go/cla#troubleshoot (Public version).
• The email used to register you as an authorized contributor must be the email used for the Git commit. Check your existing CLA data and verify that your email is set on your git commits.
• The email used to register you as an authorized contributor must also be attached to your GitHub account.

ℹ️ Googlers: Go here for more info.

[RylanSchaeffer]

I think I should probably add a test case for expectile regression-naive, maybe a modified version of QuantileRegressionLossTest(parameterized.TestCase) (https://github.com/deepmind/rlax/blob/master/rlax/_src/value_learning_test.py#L720). Would that be the right place to start?

[RylanSchaeffer]

@googlebot I signed it!

[mtthss]

I think I should probably add a test case for expectile regression-naive, maybe a modified version of QuantileRegressionLossTest(parameterized.TestCase) (https://github.com/deepmind/rlax/blob/master/rlax/_src/value_learning_test.py#L720). Would that be the right place to start?

Yes please

[RylanSchaeffer]

@mtthss , just to update you, I'm hoping to finish this next week. I'm slammed with psets and then the NeurIPS poster deadline, but I'm optimistic I'll have time over the weekend or next week.

[mtthss]

Perfect, thx for the update!

[mtthss]

Hello @RylanSchaeffer any chance we could finalize this?