Add ParabolaEnv. #29
Merged
Add ParabolaEnv. #29
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
AdamGleave
requested changes
Jun 30, 2020
src/seals/diagnostics/parabola.py
Outdated
| self._bounds = bounds | ||
|
|
||
| super().__init__( | ||
| state_space=spaces.Box(low=-bounds, high=bounds, shape=(5,)), |
There was a problem hiding this comment.
Bounds seems wrong:
- The last three components (a, b, and c) are always in
[-1,1]whateverboundsis set to. - The first two components (x, y) we say are
$\mathbb{R}^2$ in the DERAIL paper. We should either change the paper or the code.
There was a problem hiding this comment.
The motivation for bounding is more of a technicality than a environment design point: I just wanted to make sure that returns were bounded, (without the bounds, arbitrarily bad policies can get arbitrarily negative returns); I'd rather add that to the paper than change the code.
Codecov Report
@@ Coverage Diff @@
## master #29 +/- ##
============================================
+ Coverage 88.87% 100.00% +11.12%
============================================
Files 20 21 +1
Lines 593 619 +26
============================================
+ Hits 527 619 +92
+ Misses 66 0 -66
Continue to review full report at Codecov.
|
AdamGleave
approved these changes
Jun 30, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.