Neuro-Reckoning May Reduce MMOG Time Lag

Hugh Pickens writes "Time lag can cause some very strange behavior in massively multiplayer online games when players' actions onscreen become slow and jerky. New techniques are on the way to reduce the problem of lag time in MMOGs when a player's computer can't keep up with changes in a shared online world. Games like Quake use a technique called dead reckoning and while traditional dead-reckoning systems that assume that a game character will maintain the velocity and direction that it has at the moment an update is sent to all other participating computers; dead reckoning works best for movement and shooting and less well for erratic actions such as interacting with objects or with other players. Read the abstract of new technique called 'neuro-reckoning' that may improve the predictive process by installing a neural network in each player's computer to predict fast, jerky actions."

Sounds feasible

Since MMOs involve lots of repetitive actions that can easily be automated it shouldn't be too hard to predict what the player will do. OTOH this is kind of an admission that MMOs are so dumb that players are pretty predictable. I guess that's why I'm not playing an MMO currently...

(cue the Eve spam)

Not that kind of intelligence

The article is not talking about that kind of intelligence. They are talking about split second intelligence. They are talking about being about 500 msec of packets being the main scene...

Re:I kinda doubt it

If I arrived at, say, Westfall (to give a low level example that anyone who's ever played WoW will have seen)

For the Horde, you insensitive clod!

They need a neural network for what exactly?

...to predict fast, jerky actions.

Sorry, but that has to be the QOTD, made me ROFL.

Neural nets

Looks interesting, but using Neural nets would require massive amounts of computing power, compared to the more simple dead reckoning. Or at least that was the case when I worked with neural nets 12 years ago - better/faster algorithms might have been made since then.

But then again, the CPU's are so fast today, that it might not be an issue at all.

So the logical next step is...

... if the Neural net can predict my next move, just let it make it for me. Send my bot out to farm Karazhan for me while I watch the hockey game. Oh wait...

They already use it!

To control the automatic weapons firing at aircraft in south africa!

Uh.

OK, so shooting games, where you traditionally need to move as erratically and unpredictably as possible to stay alive and kill effectively, are well predicted by dead reckoning; MMOs, where you generally move directly from one beast to the next waiting for your skills to kick in, are not?

If I had to guess, the real problem is probably that commercial, hugely-trafficked MMO servers don't want to send as much data to each client as some guy's dedicated server in his basement that's only visited by thirty-two clients at a time. This probably results in the player and server updating each other less frequently.

Still, since in the MMO there are usually pretty predictable things the player will be going to next (the item on the ground, the nearby mob, the NPC in his path), maybe this will work well after all.

Quake's Lag

Would it be akin to Quake's lag or to the later versions of Quake? I never cared for how lag was "felt" following Quake I. QW through Q3 (I haven't played any others) all would make you feel like you weren't lagged at all but then suddenly you would show up dead as you caught up to real time. At least with Quake I you could "feel" the lag and make the proper adjustments.

Re:Quake's Lag

That actually has more to do with latency than number of updates. Latency determines how long until you feel an action from that was updated to the server. If everyone has 200ms ping, then someone shoots you, and that shot is updated to the server 100ms later, then you feel the hit 100ms after that, for a total of 200ms. Within that 200ms, you'd have ample time to hide behind a box or the corner of a wall, but the server would still say you were hit (because 200ms ago you weren't behind that box or wall on your enemies computer). This retroactive update is how modern systems work, and it reduces apparent shooting lag.

Sidenote: This began the misconception that lag time benefited the lagger, or that laggy players lag the whole server, neither of which is true. The quicker your ping time, the faster your shots or actions will register on the server. If a high ping bastard and low ping bastard shoot each other at the same exact moment, the LPB will have his shot register first, and the HPB will die.

Originally, shots and hits were always done actively at the time it reached the server. So if you had 400ms ping, you'd see your gun shoot 400ms after you fired it. This made lag almost unbearable for most high ping players, because if they shot at you, they'd almost always miss, because by the time their shot registered, you would've moved out of the spot you were standing a split second ago.

As for the article, it's dealing solely with player movement on MMORPGS, which is determined by the rate of updates (how many packets get sent out per second). Player action updates are always triggered at the time of action (such as casting a spell), however, movement is an ongoing process. Basically your client updates the server around a dozen times a second with position and velocity information, because of your movement. However, it always assumes you'll stick to that velocity (moving forward? dead reckoning predicts you move forward some more) in between updates. If you deviate from your predicted movement along a velocity, you need to send an update to the server. This new method will predict what movement you'll take, rather than always assuming a straight line from your current movement.

My student ACM account doesn't have subscription to access the article, so I'm not entirely sure, but this is my take on what it does:
For instance, if you're moving forward, and there's something in front of you, the neural net will attempt to determine that you'll probably move in a different direction, and send that as your predicted velocity. If it turns out you don't move that direction, you'll simply have to send another update. If you do move that direction (which statistically you should), then there will be no need for an update, thereby saving bandwidth. These predictions and updates happen at a rate which makes it seem like your player is moving smoothly, when in reality, there's a bunch of micro deviations and stuttering.

Could be helpful in other ways

If they're adding a neural network to help them predict actions. If it works, couldn't the system be used to enhance reflexes on the player's side?

Everyone's had an incident when they said "Every time X happens, I want to instantly do y.". Or something more complicated like moving in such a way as to not get flanked. Speeding up repetitive trading or moving activities and so on. Of course, this level of automation might seem too much like giving an unfair advantage. But personally I'd really love a game that helps me play better.

I tried letting it predict Slashdot...

The results: "First post!" "Step 1: Teach neural network to farm gold. Step 2: ??? Step 3: Profit!" "In Soviet Russia, you predict the actions of neural networks!" "I for one welcome our neural network overlords" "But does it run Linux?" "Imagine a Beowulf cluster of these!"

all about prediction

If the computer is going to predict my next move, I might as well let the computer play the game. If the algorithm is using a neural network, the computer will become just like me as time passes. The main difference between a good player and a normal one, is the difference from the nominal behaviour. Thus making this method of uterly useless.

So in other words...

If you are lagging the server will switch you to a NPC until you packets get in. It is funny how academics like making things seems more complex then they actually are. Verses other way which generally keep you on your current path, which is easier to program.

Alternatively...

They could put some work into the technology used to actually CONNECT to said servers. Increased compression, lowering latency all around, smarter load-balancing, making ISPs keep up with the times... Why not actually fix something instead of just putting a band-aid on it?

looks like this was cribbed from Microsoft

See: http://www.xnagamefest.com/talk_abstracts.htm [xnagamefest.com], and scroll down to the abstract for Donnybrook.

Details are a bit skimpy in the abstract, but if you do a bit of searching, you can find the presentation material. At the conference they showed a demo with 32 bots crammed in a pretty small map in Quake. On one screen they were running the original version, where it was really jerky with that many bots. On the other screen they were running their modified version, where the motion was perfect.

Please oh please let this be prior art to Microsoft.

Old news

Weren't we just reading about the beta test yesterday? Robotic Cannon Loses Control, Kills 9 [slashdot.org]

Insolvable problem

You know, the only real solution of the problem is to make your network latency 100ms. No other solution will work. Maybe the neural prediction thing works better than dead reckoning in some situtions, but it never will be anywhere near as good as playing on a fast network

No need

Just do what Valve did with HL2. Remove prediction altogether by time-shifting all clients back by 2-3 server updates. That way everything the client renders has already happened, and there is no possibility of making a mistake.

I think this would help if implemented properly...

Games like DAoC and Planet Side can already support hundreds (100 - 300) people at the same time with sides trying to fight each other. (Limit is no longer video cards)

Other MMOs have failed miserably and have added something called "instancing" where they even instance peaceful zones. These type of crappy games with crappy programmers will not benefit from anything.

Pure first person shooters (Battlefield, quake) tend to limit it to 64 or 32, because they want to be more precise and send more detailed packets to show what the character is doing. They also register hits differently, as there are primarily ranged attacks, instead of hand to hand (Planetside followed the MMO model here and no the FPS model, though it could be classified as an FPS no problem).

In short, I believe an MMO that already has good networking support (i.e. smart networking coders) can utilize this and gain benefit.

Lag and all

The problem with MMO's are they often try and predict what the player is going to be doing. You often find yourself somewhere you are not expecting. In World of Warcraft this can bee seen by other players as rubber banding, you character moves forward and backwards erratically or in Dark Age of Camelot where players produce artificial lag which causes the same effect but the game allows you to do actions while you are lagged such as casting, changing directions and others.

All predictions in MMO's save on bandwidth needed to actually play the game at the expense of player enjoyment.

The only question left for the consumer is this behavior acceptable to you?

Now where this new "neural network in each player's computer to predict fast, jerky actions." Is interesting but flawed. You can't have this stuff on the client computer. If you have never played a MMO, it my regret to inform you that, everything client side can be and will be hacked and taken to pieces to gain any advantage against fellow players.

QQ

Data corruption

I wonder how smart this "neural network" would actually be.

For instance, say I'm playing a game of (Popular FPS A) with a bunch of people online, and I understand how the neural network works. Couldn't I just repeatedly move left to right in a jerky fasion for a bit, and then run straight toward my enemy? If they lag, the neural network computations will show me as moving left to right, where I'm actually just running straight...

MOM

Manager
Of
Movement

MOM always knows what you're doing before you even start to think about it.

This is ridiculous

The only time such reckoning really matters is in PVP, and most PVP players who know what they're doing jitter about like caffeine addled monkeys. Either the latency is low enough to get an accurate postion, or it's not and my largely random hammering of WASD as I try to move in and out of you viewing (casting, swing, etc.) arc isn't going to provide that much predictive information.

Re:Hacks

I would imagine that it can't be any easier than hacking the current dead reckoning implementations.

Re:Hacks

how could you possibly get an unfair advantage? all the actual calculations are still done server side. Most mmo clients are nothing more than a glorified chat program, the servers do most of the work.