Eugene Vinitsky
Eugene Vinitsky
So uh, this passes. Can we merge it @AboudyKreidieh ?
Putting aside the build failure, this sets RLlibs DQN as the default option. We'd prefer you make it so that there's a choice of algorithm, of which DQN is one....
Well, not quite. The implementation of TD3 in h-baselines is not identical to the rllib one.
This looks good to me minus comments! @pengyuan-zhou if the changes are made I will merge.
Argh, this is what I was afraid of. Build is failing, probably because of the visualizer tests.
Thank you for this contribution! I'm currently flying but will review this once I land!
Thanks so much for this! Could you add an example of its usage?
Oh wow I didn't see how complete this is. You can obviously just grab the branch now but unfortunately we need to write tests for this to merge it into...
There's even a tutorial! Amazing job @vallout
Oh I missed these reviews! These are all good; thank you!