Add scale_rewards_by_dt flag to disable reward time scaling #455
+101
−4
Conversation
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
Implements a configurable flag to control whether rewards are scaled by the environment step duration (dt). The flag defaults to True to maintain backward compatibility. When scale_rewards_by_dt=True (default): - reward_buf = raw_value * weight * dt - _episode_sums and Episode_Reward/* metrics are scaled by dt When scale_rewards_by_dt=False: - reward_buf = raw_value * weight (no dt scaling) The _step_reward values (used by get_active_iterable_terms) always contain unscaled values regardless of the setting. Closes #405 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
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Outdated suggestions cannot be applied.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.
Summary
scale_rewards_by_dt: bool = Trueconfig field toManagerBasedRlEnvCfgRewardManagerto conditionally apply dt scaling based on the flagBehavior
reward_buf_step_rewardscale_rewards_by_dt=True(default)raw * weight * dtraw * weightscale_rewards_by_dt=Falseraw * weightraw * weightThe default of
Truemaintains backward compatibility.Test plan
test_reward_scaling_enabled- verifies rewards are scaled by dt when enabledtest_reward_scaling_disabled- verifies rewards are not scaled when disabledtest_reward_scaling_default_is_enabled- verifies default is True for backward compatibilityCloses #405
🤖 Generated with Claude Code