[1]https://github.com/Microsoft/AirSim [2] https://github.com/udacity/self-driving-car-sim
+ Both [1] and [3] have much fewer assets (like 3D models of houses, factories, bridges, cars, trucks, and so on) you'd have to buy them on the Unreal/Unity model marketplace and it still wouldn't be enough. Autodrome can take advantage of almost entire Europe and a third of USA at 1:20 scale.
+ Autodrome has a sparse map representation that is really easy to randomly fuzz. I.e. it's easy to shift a segment of the road a little bit and see how the algorithm would react to the fuzzed scenario. I believe this is only way how to achieve robust agents and effectively prevent testing on the training set.
- Biggest disadvantage of Autodrome is a lack of access to in-game dynamic NPCs (like other trucks, cars or pedestrians). As far as I know there's no API for this. Without help (or a lot of very fragile memory hacking) from the developers of the game this feature is very hard to achieve and both [1] and [3] already have it.
[3] http://carla.org
PS: Keep in mind that I'm the developer of Autodrome so I my objectivity is very questionable.
Would you mind if at some point I share your project at https://weeklyrobotics.com ?
If we had spent as much on genetic research as we did on the moon landing we could have had fire breathing dragons. Think of all the spin offs from that that we are just starting to see now, we could have had them sooner.