Can I use NeoRL, to generate a dataset, in the d4rl format, e.g for the finance environment? about neorl HOT 2 CLOSED

Hi Krishna,

Thanks for your interest in our work. For the finance environment, we provide up to 1000 trajectories of training data, which is roughly 2M transitions. You can change train_num=1000 in get_dataset to get the full dataset. The dataset is already quite large in our sense, but in case you really need to generate more data, use can use the get_data.py in our repo to do that.

To convert our data to d4rl format, you just need to map the keys, e.g. obs -> observations. Besides, we use index to mark the end of each trajectories, you should convert that to timeouts in a proper way.

from neorl.

Brilliant, 2M is good enough to get me started, thank you very much ! Cheers, and thanks for the great paper and code !
Krishna

from neorl.