Fix PositionBonus wrapper ignoring the scale parameter (issue #473) - #505
Open
teddytennant wants to merge 1 commit into
Open
Fix PositionBonus wrapper ignoring the scale parameter (issue #473)#505teddytennant wants to merge 1 commit into
scale parameter (issue #473)#505teddytennant wants to merge 1 commit into
Conversation
PositionBonus.__init__ hardcoded self.scale = 1, so the scale argument was silently discarded and PositionBonus(env, scale=k) produced the same reward for every k. Assign the scale argument instead and document it. Add a parametrized test that exercises non-unit scales.
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
PositionBonus.__init__accepts ascaleargument but hardcodedself.scale = 1, so the argument was silently discarded.step()computesreward += bonus * self.scale, meaningPositionBonus(env, scale=k)returned identical rewards for everyk. This changes the assignment to use the passed-inscaleand documents the parameter in theArgs:docstring.Why
The
scaleparameter (added in #433) had no effect at all — the exploration bonus was always multiplied by 1 regardless of the value passed. See #473.Testing
Added
tests/test_wrappers.py::test_position_bonus_wrapper_scale, a parametrized test overscalein{0.5, 2, 3.0}that checks the wrapped reward equalsbase_reward + scale * bonus. It fails onmain(rewards are unchanged byscale) and passes with this fix.Fixes #473