Two months to advance the state of the art on a complex physics-based game with branching paths. Current approaches such as DQNs or god forbid DRL[1] barely reach the performance of my three year old cousin in atari game score maximization and are mostly non-transferable to new levels... Good luck.<p>[1] <a href="https://www.alexirpan.com/2018/02/14/rl-hard.html" rel="nofollow">https://www.alexirpan.com/2018/02/14/rl-hard.html</a>
I'm a big retro Sega fan, and I've always wanted to look into doing something like this, but this seems... really difficult. Would the best approach be to jump right in and hope for the best, or are there any sources I should look into?
The demo GIFs show Sonic 1 and 3, but all 3 Genesis games have slightly different physics and mechanics which could trip up an AI if not trained on all 3 games. Is the challenge just using the Sonic 1 engine?
I'm wondering if there's a MOOC that takes you from zero to being able to build a system that learns how to play such a game, maybe focusing a bit less on the math (especially the proofs). I took Andrew Ng's course on Coursera but I feel like the gap between what I know and what's needed for this contest is huge. Am I wrong?
Seems like a stretch to call this “transfer learning”. Maybe training on Sonic and testing on Mario.<p>Would be cool to see some kind of adversarial competition. You train to, say, beat a game level but you test to beat someone else’s submission. (Short on the specifics, I know.)
I expect training & testing to make use of emulators & ROMs - wouldn't Sega potentially have a problem with this or is it considered fair use?
Can we move away from video games ? I know games provide a closed loop for these kind of experiments/contests, but I want to see more practical application of RL. How about code generation that create programs based on the test cases or RL agent that can use a 3d design software.
Couldn't a new level contain some sort of new scenario that would be completely impossible to navigate based on previous experience without some <i>very</i> general AI?
Is this a fair representation of a human playing a game? Usually as a human player I don't go into a level expecting to clear it never having seen it before.