Add cogames.cogs-v-clips install/training command #400
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
relh changed the title This reverts commit 06f8e9f.
github-merge-queue bot pushed a commit to Metta-AI/metta that referenced this pull request Oct 30, 2025
I'm not sure what's needed to package cogames to work with `pip install pufferlib[cogames]` but this seems to be sufficient. Paired with: PufferAI/PufferLib#400, it enables: ``` Install (pip or uv/pip): pip install setuptools numpy torch Then: pip install pufferlib[cogames] --no-build-isolation Train: puffer train cogames.cogs-v-clips.training_facility.harvest or: puffer train cogames.cogs-v-clips.machina_1.open_world Everything currently runs but it's hooked up to a few simplifying variants: lonely_heart = less resources per heart heart_chorus = shaped rewards via diversity etc ``` [Asana Task](https://app.asana.com/1/1209016784099267/project/1210348820405981/task/1211773293280028)
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 Outdated suggestions cannot be applied.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.
Install (pip or uv/pip):
Then:
Train:
or:
Everything currently runs but it's hooked up to a few simplifying variants:
puffer train cogames.cogs-v-clips.training_facility.harvest --train.device cpu --vec.num-workers 12 --vec.num-envs 144gets to hearts:agent/heart.gained 9.240in 20m on a macbook