Overwatch's Competitive Mode

Dear Jeff Kaplan and the Overwatch team,

I think your game is great and it's not lightly that I rate it a 10 out of 10. Respectfully though, I think you're a bit lost in the woods on how the competitive mode should work. That's understandable because it's a complicated problem that's nearly unsolvable given your constraints.

While this post by Kaplan is excellent about sharing thoughts from the dev perspective, I'm concerned about the specific thoughts laid out there.


"right now we’re exploring ways to allow for matches that would otherwise result in Sudden Death to instead resolve in a draw where neither team wins or loses." —Kaplan

You should not consider adding draws to the game. In a tournament setting, it's simply not acceptable. For single and double elimination tournaments, a single winner must advance for the tournament to work. In a swiss tournament (especially if there is a cut to top 8 for a single elim portion), every ounce of draw that exists causes problems. I think explaining what those problems are is beyond the scope of my post, though I'm happy to do it if needed. For my own tabletop game tournaments, the rules make match draws impossible (though game-draws within a match are still technically possible, since it's match-draws that are the real issue).

Anyway, draws range from bad news in swiss to literally infeasible for single and double elimination tournaments. If you implement them, then tournaments will use some other system, and probably one you won't like. You should feel GOOD about the format used in tournaments though, and it's best if they use the same format you come up with for the in-game competitive mode.

The Fundamental Issue

The reason why this is all so hard, as you know very well, is that a competitive format wants an ODD number of rounds, such as 2 out of 3 or 3 out of 5, but the asymmetric modes you've created want there to be an EVEN number of rounds so each team gets the same number of chances on offense and defense.

The other issue, as you well know, is that there is a Venn diagram of "what actually works" and "what people will accept." We have to find the intersection and unfortunately reject things that "actually work" if people won't accept them. Which brings us to the first try you had at a competitive mode during the beta.

The King of the Hill Tie-Breaker

People kind of didn't like this, but your dev team thought it was good because it worked. Actually, you might have drawn the wrong conclusions from this? People had various different objections as you laid out in your post, but consider these two issues:

1) It shouldn't be "sudden death"
2) People don't like that it's "a different map"

The King of the Hill tie-breaker was framed as "a tie-breaker" and "sudden death" but it really shouldn't be. Remember that the fundamental problem is that a competitive format wants an ODD number of rounds, so it's probably best if our solution has that. That means the king of the hill thing is "the third round", NOT sudden death. It should be as long as a full round and given equal weight.

One complaint I heard was that some players thought it was stupid that they might barely lose round 1, then win round 2 by a landslide, but then lose the match by barely failing at the tie-breaker, and it felt stupid. My initial reaction to that train of thought is that the complaint itself is stupid. After all, in that example, the complainer did lose 2 out of 3.

There's an important principle that "a win is a win." That means it's generally bad to count "different kind of wins" (such as win by a lot or win by a little) because it's too game-warping and generally leads to crappy dynamics. Strategies that barely win should be just as viable as those that happen to win by a lot sometimes. That alone is reason enough to make sure that there aren't extra stats attached to a win, but even beyond that, if you do actually win, it feels really crappy to be penalized that it "wasn't by enough."

So the complaint here, at first glance, it stupid because it's actually advocating the opposite of "a win counts as a win." But looking more closely, the real source of that complaint isn't that. It's that round 3 was not a real round. It was way too short and felt unfair to lose based on its outcome. I think this particular complaint evaporates if you frame it as a real, full round 3 (and design it to actually be that, too).

Another complaint is that it feels bad to be transported to a different map for round 3. Yeah ok, that's valid. Have you noticed that no one complains that you're transported to different maps over the course of King of the Hill rounds though? Each one of those takes place on a totally different map, but the trick there is that the graphics and theming make it FEEL like it's "all the same map." It's all "Nepal" or "Ilios" or whatever. Maybe if you made king of the hill maps that looked like they were part of each other map, it would have gone over better (for example, the king of the hill version of Dorado, etc.)

If you made round 3 a full round and you themed it so it felt like you were on "the same map," there are still other problems that remain. First, it's a different game mode still. And second, some people think king of the hill is too chaotic and wish that it wasn't what round 3 was about.

Yeah ok to both of those, but our constraints are so big here that maybe that's the best course anyway. Perhaps you could devise some OTHER symmetric round 3 that isn't king of the hill if you wanted to address those.

Current Competitive Mode

Moving on to the mode that's in the game now. This one uses an asymmetric mode for the "tie breaker". As you have seen, people don't really like that. I'm totally with you that it can work and be balanced on the razor's edge of 50-50 fairness. I have no doubt about that. But we're dealing with people's perceptions, and it might be they will just never accept this thing about a coin flip that then puts one team on offense for the final round, even if it were fair. So for this reason alone, you might have to abandon the current system.

But the point I'd like to make is that there are two OTHER problems with the current system.

1) The tie break system is really inefficient.
2) It's game-warping

Remember that the entire thing we're hoping for here is a "round 3" so that we can determine a winner if rounds 1 and 2 fail to do so. But This current system adds a round 3 AND round 4, basically. Then it can sudden death after that? That's a long way to go, having 5 different starts, when the thing we actually want is 3. Also, it's just pretty confusing. I watched a streamer who had been playing *8 hours* straight of competitive mode, and he failed to understand if winning or losing a certain round was going to determine the match win or loss, or if there'd be more gameplay after. I confess I also couldn't follow it at first either.

About the game-warping thing, consider the stopwatch method. That's the thing where team A completes a round in 4 minutes 20 seconds or something, then team B has to beat that time. You don't like that. I don't like it either. It's violating the "win is a win" concept and it's favoring certain strategies in a boring way. Strategies that are meant to waste time without killing are X powerful already, but their power level increases quite a bit if the clock is very short. In other words, wasting time without even killing the opponents is naturally sort of good, but usually it can't go on forever. Opponents can eventually overcome it. But if there's only 2 minutes on the clock to begin with, it's a huge boost to those lame tactics. You don't really want your game to be all about Tracer harass time waste + double Winston time waste.

The current in-game competitive mode HAS that same crappy property of stopwatch though. That's what the "time bank" system is. If you complete an objective very fast, but your opponents complete it slowly, then round 3 and round 4, one team will have to play at a huge time disadvantage. So "a win was not a win" there, and also we get game-warping surrounding time-wasting techniques.

Basically, the current system is falling pretty far short of just having a round 3. If it did that, it would shorter, it would be less confusing, it would preserve "a win is a win", and it would not be game-warping.

As an aside, I'd like to say that the overtime system used by all modes (an extra bit of time if anyone on your team is on the objective, even when the clock ran out) is fantastic. It's exciting, it feels good, it allows comebacks, it prevents "lame duck" situations where one side can't possibly win in the time remaining, and allows more possible strategies by not overly favoring those that try to win fast. Thumbs up on all that.

Minimizing Tie Breakers

Another concept here is minimizing how often you need a tie breaker in the first place. I saved this for last because I think it's the LEAST important part. Unless tie-breaks are minimized to literally 0%, it means we still needed the entire discussion we just had anyway. So let's consider these two cases:

1) We actually do minimize tie breaks to happen 0%
2) We don't go down to 0%, but we still want to minimize them as much as we can.

To have tie breaks happen 0% of the time, that means after round 1 and round 2 are played, we'd always know the winner. The stopwatch system is the obvious way to do that, but it's just not a good solution. Anti-climactic, usually not great to watch, and game-warping. But...there kind of isn't another way? If both teams complete the objective, and you can't decide a winner based on time, and you can't call a draw, then you'd have to break the tie based on some other "score" which is always going to feel wrong.

Moving on to minimizing tie breakers (but not forcing them to happen 0% of the time), you're actually kind of stuck here too. There'd be less need for a round 3 if payload maps were 2 or 3 times as long (or the payload traveled 2 or 3 times as slowly). That way it's far more likely that tie can be broken based on how far you get. That's kind of immediately bad though, because your maps already have around a 50-50 win rate on offense vs. defense across your player population. So making the competitive mode into like 10-90 (favoring defense) intentionally just to minimize the chance that both teams will complete the objective is really screwy.

In other words, you're kind of destined to forever have at least as many ties as you do now from the specific case of both teams completing all objectives. The only real way to make headway here is to minimize the ties in the cases where NEITHER team completes the entire objective, and you've already done that. Incidentally, this violates the "a loss is a loss" principle, but somehow that seems more acceptable than violating "a win is a win," so I have no objection here. While getting a win (even by a narrow margin) feels like it should "fully count", if you get "half a win" (aka, a loss) against someone that got even less than that, it feels legit to beat them.

Closing Thoughts

Here's the TL;DR

  • Draws are bad and should not be considered.
  • You're probably forced to have a symmetric way of resolving ties, like it or not. It could be king of the hill, or a new thing you create.
  • That symmetric thing should be a full round 3, not a "tie breaker" or sudden death thing that's really fast. It should have the same duration and weight as other rounds.
  • It should use the same map graphics as the map you played in round 1 and 2, even if it works differently.
  • The current system has an asymmetric resolution (that people don't like, even if it works), is inefficient at producing a winner quickly, confusing, and also game-warping.

I'm sure you guys will figure out something good since the rest of the game is so superb. It's a difficult problem.