Open pseudo-rnd-thoughts opened 7 months ago
The latest updates on your projects. Learn more about Vercel for Git ↗︎
Name | Status | Preview | Comments | Updated (UTC) |
---|---|---|---|---|
cleanrl | ✅ Ready (Inspect) | Visit Preview | 💬 Add feedback | Dec 6, 2023 0:30am |
@vwxyzjn Do you want to rerun all of the scripts because the final evaluation data is not used commonly or can this just be merged without?
Description
Bug fix for https://github.com/vwxyzjn/cleanrl/issues/429 I could repeat this for all DQN, C51 agents that have an
end_e
argument to prevent this issue in the future A potential alternative change is to add a new parameter for the evaluation epsilonTypes of changes
Checklist:
pre-commit run --all-files
passes (required).mkdocs serve
.If you need to run benchmark experiments for a performance-impacting changes:
--capture-video
.python -m openrlbenchmark.rlops
.python -m openrlbenchmark.rlops
utility to the documentation.python -m openrlbenchmark.rlops ....your_args... --report
, to the documentation.