Fix wrong world vector range in training loss calculation

[jonathansalzer]

Throughout training and inference, a world vector range of (-2; 2) is consistently used. However, during loss calculation, the world vector range is not explicitly passed to the action tokenization function, causing it to default to a range of (-1; 1). This mismatch leads to scaling issues: values are doubled, as well as clipped if they exceed the range (-1; 1).

By passing the model world vector range to the action tokenization, this issue is resolved.

[AoqunJin]

I found this due to the poor performance of the trained model when tested. But it's solved now, took days to debug 😂😂