Can a customized env be added to the current framework?

google-research / batch_rl

Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

https://offline-rl.github.io/

Apache License 2.0

536 stars 75 forks source link

Can a customized env be added to the current framework? #19

Closed blurLake closed 2 years ago

blurLake commented 3 years ago

Hi, I am new to this repo and offline setting for RL. I guess it should be possible, but still would like to hear some suggestions from the pros. More importantly, if it is possible to add new gym env, how to prepare the offline data?

Thank you very much!

agarwl commented 3 years ago

@psc might answer more details .. but Dopamine supports openAI gym environments too and there is data logging code in the repo (look in the baselines directory) that can be used for any env supported by Dopamine.