Selfplay fixes - #685
Merged
Merged
Conversation
The ladder eval hardcoded 8192 envs. That suits bots that are just code, but an env whose bot is an external process spawns one child per env, so thousands is not viable. Add [selfplay] eval_bot_envs to set the count and eval_bot_threads to raise vec.num_threads for the eval only -- a bot that blocks on IPC is paced by how many envs step concurrently, not by how many exist. Both default to the previous behaviour. Replace the SELFPLAY_LADDER_ENVS define with the config key, which now carries the value and the rationale. Also: eval_loop hard-exited when [sweep] metric named a trainer-level overlay such as selfplay/bot_ladder_perf, because the env log cannot contain a key the ladder computes from those very evals. Fall back to env/score; the ladder scores off perf and ignores this value. Drop a stray double blank line in constellation.c.
l1onh3art88
changed the title
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Selfplay missing metric compatibility issue with constellation on eval bots.