Closed micahcarroll closed 2 years ago
I believe that this line should have a <= rather than a < in order for the code to not cut out the best performing trajectory even when using pct_traj = 1.
<=
<
pct_traj = 1.
https://github.com/kzl/decision-transformer/blob/f04280e3668a992c41b38bdfb6b6181d61b4dc52/gym/experiment.py#L109
To replicate, use a dataset with 2 trajectories and use pct_traj = 1. and the resulting num_trajectories will just be 1 rather than 2.
num_trajectories
Thanks for catching this! I think you're right.
I believe that this line should have a
<=
rather than a<
in order for the code to not cut out the best performing trajectory even when usingpct_traj = 1.
https://github.com/kzl/decision-transformer/blob/f04280e3668a992c41b38bdfb6b6181d61b4dc52/gym/experiment.py#L109
To replicate, use a dataset with 2 trajectories and use
pct_traj = 1.
and the resultingnum_trajectories
will just be 1 rather than 2.