Update "Stopping Criteria" Runner docs

Co-authored-by: Joseph Weston <joseph@weston.cloud>

Author: basnijholt

docs/source/reference/adaptive.runner.extras.md

@@ -6,10 +6,9 @@ Runners allow you to specify the stopping criterion by providing
 a `goal` as a function that takes the learner and returns a boolean: `False`
 for "continue running" and `True` for "stop". This gives you a lot of flexibility
 for defining your own stopping conditions, however we also provide some common
-stopping conditions as a convenience. The `adaptive.runner.auto_goal` will
-automatically create a goal based on simple input types, e.g., an int means
-at least that many points are required and a float means that the loss has
-to become lower or equal to that float.
+stopping conditions as a convenience. For example, to continue until the loss is below a threshold `x`,
+you may specify `loss_goal=x`. Similarly, to continue until `n` points have been sampled, you may
+specify `npoints_goal=n`. See the Runner docstring for details.
 
 ```{eval-rst}
 .. autofunction:: adaptive.runner.auto_goal