Would be fun to experiment with the data and see if it would be possible to infer game tactics from professional players and "simulate" those against another bot based on the current game state.
There are probably too many variables in Starcraft for this to be practical. With a game like chess there's a fairly obvious set of state variables to keep track of (max of 32 pieces that each have a position in essentially an 8x8 2D array), with Starcraft it's pretty nuts though, each side can have dozens of buildings, dozens of units of ~15 types, each of which has a position on a much larger grid, health, sometimes energy, status effects, etc. Obviously there are RTS games that are more complicated yet, but the jump from a turn-based board game to an RTS is just huge.
That's why it would be interesting to see how much can be inferred from offline learning first.
For example, looking at unit positions over time for the map can be quite rewarding, especially between the different phases of the game (early, mid, late).