git
ask
hub
Privacy
Terms
Sign in with GitHub
yinqibai962/d-arl
↗
Stars ·
71
Language ·
Python
License ·
Apache-2.0
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: yinqibai962
Ask anything about this repo to start.
Walk me through how D-ARL keeps a buffer of past model versions and replays their rollouts during training
Explain the variance-guided sample selection step in D-ARL and how it decides which rollouts to keep
Write a Slurm batch script that runs the D-ARL config on Qwen3-4B across two nodes
Diff the baseline shell scripts against the D-ARL script in this repo and summarize what flags change
Show how to plug a new benchmark into the D-ARL evaluation pipeline
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).