search

takuseno / d4rl-atari

Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)
MIT License
101 stars 14 forks source link

Can the data be split into trajectories? #10

Open Miguel-s-Amaral opened 2 years ago

Miguel-s-Amaral commented 2 years ago

I am currently attempting to divide the data into trajectories for my replication of decision transformer is there any way i can do this?

Thanks a lot

GilgameshD commented 2 years ago

I think you can use the 'terminal' dimension to split

takuseno commented 2 years ago

@GilgameshD is right. Please split trajectories based on terminal flags.