Closed stevenyangyj closed 1 month ago
@PeterAJansen can correct me if I'm wrong, at the moment there's not easy way to generate a visual observation from the textual description.
Sorry to be slow responding to this one. I can't think of an easy way of doing this in ScienceWorld, but we have just released DiscoveryWorld that includes both text (i.e. JSON) and proper visual (2D tile-based) observations. Here's the link for DiscoveryWorld: https://github.com/allenai/discoveryworld
If it /must/ be ScienceWorld that has the visual observations, the potential ways forward that come to mind are:
Thanks for your help!