parallel-trpo
parallel-trpo copied to clipboard
kvfrans
A parallel version of Trust Region Policy Optimization
Hello, under what license is this project released under ? I would like to study it to learn from it. Thank you.
Is there any way to load trained weights and use them for further training?
Work in progress. It's running but not training (seems to not update the policy).
Hi, i saw on your blog post about the upcoming experiments on "humanoid" i wonder how it goes ;P
