search

jannerm / trajectory-transformer

Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"
https://trajectory-transformer.github.io
MIT License
464 stars 65 forks source link

Question about the visualisation of four-rooms #9

Open louieworth opened 2 years ago

louieworth commented 2 years ago

Hi,

Here I saw the paper where you drew the trajectories of four rooms environment in Figure 6. Where the observation in this environment is based on pictures, could you share your code about how you draw the trajectories?

louieworth commented 2 years ago

It's likely that your paths are continuous, but I got all the positions from the environment is discrete.

Liang-ZX commented 1 year ago

It's likely that your paths are continuous, but I got all the positions from the environment is discrete.

Hi, I met the similar question. Would you please tell me where to find the implementation of TT in four-rooms environment? Thank you.