We have seen advances in top down, RTS team games like Dota 2 and Starcraft II from companies like OpenAI who developed agents to beat real pro players most of the time. How would similar learning techniques compare to games like Overwatch that require faster reaction times and complex understanding of 3d space and effect? Or have we not developed solutions that could be tasked with this problem?
-
$\begingroup$ Apologies if this is a bad question or one that isn't for this forum, I just signed up. $\endgroup$– MaxJun 12, 2019 at 8:43
-
$\begingroup$ Hi and welcome to this community! I think that this is a very interesting question, so don't worry! Maybe I will answer it later. $\endgroup$– nbroJun 13, 2019 at 14:51
1 Answer
To get a better understanding, let's compare a couple of games DOTA2 and Overwatch. At first, both seen similar in terms of multiplayer
and strategy
, but there is a significant difference.
You have mentioned it in the question. reaction time
Even though both the games require strategy and understanding of the surroundings and team play, FPS games are heavily dependent on reaction time
and accuracy
. As much as you try, it's next to impossible to reach the reaction times and accuracy of computer agent.
In games such as DOTA2, the game is more dependent towards strategy
and how the characters interact with each other (Strengths and Weakness).
Finally, it doesn't make sense to train an AI based agent to play FPS games, because the optimal solution is already present and there is no way that AI can reach those levels. It's called AIM BOT. As good as you can get at strategy and planning, team work and reaction times, you can almost never beat it. It's next to 100% accurate and the opponent is basically dead as soon as he's in sight.
-
$\begingroup$ Thanks for this answer! As for aimbot, I'm sure you could win against a team of badly coordinated aim-botted with a well coordinated team (perhaps not in other fps games). I was interested in how agents could learn to work with each other in these type of enviroments, but considering how well the dota agents performed in teams, I doubt this will be the least of its concerns. If someone or some people decide to teach a bot to play overwatch I think the main issue will be the visual perception of the game and the quick response times. $\endgroup$– MaxJun 14, 2019 at 9:21