Conversation
Complete SAC Atari benchmark across all 58 games (2M frames, 4 seeds). Single universal spec (sac_atari.json): training_iter=3, Categorical, AdamW lr=3e-4. A2C+PPO+SAC comparison plots and HF data graduated to public repo. Streamlined CLAUDE.md and benchmark skill. Removed stale SAC PER specs. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
kengz
force-pushed
the
feat/sac-atari
branch
from
b4f7f97 to
faf3d90
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
sac_atari.json): training_iter=3, Categorical, AdamW lr=3e-4Results
SAC generally underperforms PPO on Atari (wins ~10/58 games), useful as negative result.
Best SAC games: CrazyClimber 81839, Atlantis 64097, VideoPinball 22541
Worst SAC games: Tennis -374, FishingDerby -77, DoubleDunk -44, Enduro 0, Freeway 0
Test plan
🤖 Generated with Claude Code