Interesting question! I assume in the Bot/headless mode, it's pretty optimized to skip the part needed for rendering, but you still need to do enough physics and other state update.
Best case, I'd assume at least a few ms per tick, because games become as complex as possible and still fit in 30 fps (33 ms, much of which is rendering, but still much happens regardless of producing pixels).
> Maybe the DoTA code can be optimized x2 for self play?!
Please don't. Every time they change something, several other things break.
Ok, just kidding.
But their fix logs are really look like the game logic is built by adding a hack on top of a hack with no automatic testing. Everything seems to hold on the playtesting.
> This logic takes milliseconds per tick to execute, versus nanoseconds for Chess or Go engines.
So this is game engine itself, taking up the CPUs. Maybe the DoTA code can be optimized x2 for self play?!
IIRC AlphaZero was about x10 more efficient than AlphaGo Zero due to algorithm improvement.
So overall, $100K for the final training run, which maybe can go down to $10K for a different domain of similar complexity.