Slashdot Mirror
Classifying Players For Unique Game Experiences
togelius writes "Whenever you play a game of Tomb Raider: Underworld, heaps of data about your playing style is collected at Eidos' servers. Researchers at the Center for Computer Games Research have now mined this data to identify the different types of player behavior (PDF). Using self-organizing neural networks, they classified players as either Veterans, Solvers, Pacifists or Runners. It turns out people play the game for very different reasons and focus on different parts of the game, but almost everyone falls into one of these categories. These neural networks can now quickly determine which of these groups you belong to based on just seeing you play. In the near future, such networks will be used to adapt games like Tomb Raider while they are played (e.g. by removing or adding puzzles and enemies), so you get the game you want."
It turns out people play the game for very different reasons and focus on different parts of the game, but almost everyone falls into one of these categories.
Yep, I've noticed this too. I dont get why, but some people tend to stare the ass more, while personally I like to enjoy the boobs.
Did this research notice if there were any deaths caused by getting discracted when you jumped and the camera got into such position that you tried to get a nippleslip or see the panties?
After seeing how Tivo and Netflix recommendations go sometimes, I'm not sure I want a game changing itself because it thinks I know what I want. Not to knock Tivo or Netflix, they are accurate alot, but sometimes they are way off base.
Besides, if it knew what I really wanted, everything would just end up having tits.
"I don't have to think. I only have to do it. The results are always perfect, but that's old news." - Meat Puppets
Whenever you play a game of Tomb Raider: Underworld, heaps of data about your playing style is collected at Eidos' servers.
Thanks for the heads up, so I won't buy it. I personally don't like having everything I do monitored in some way on some server with a shady privacy policy.
How about the naked Lara Croft modders? Which slot do they fall into?
...15 years ago. They change the names and claim it as unique research?
HBI's Law: Frequency of calling others Nazis is directly correlated with the likelihood of the accuser being Communist.
How about having a little confidence in your designers and letting me play the game THEY made?
End of lesson. You may press the button.
They seem to have forgotten about the metagamers :)
Using self-organizing neural networks, they classified players as either Veterans, Solvers, Pacifists or Runners ... but almost everyone falls into one of these categories
I didn't RTFA but wouldn't everyone fall into one of the categories? I mean, it sounds like the system does just that: puts the player in one of the categories.
Many players enjoy some variety within a game. I've played all the Hitman games with the aim of completing the missions "cleanly", so I enjoyed the ones which force you to play the last mission as more of a shooter game (they did this in the 1st, 2nd and 4th games, while the third had a finale which offed the chance to play stealthily, but was still designed to produce a massive firefight if not played stealthily).
I would be somewhat annoyed if Eidos based the style of the final level of the next Hitman game on stats from the rest of the game, which seems to be a real possibility since Hitman is a game which offers plenty of chances to choose between stealth and action gameplay.
# cat
Damn, my RAM is full of llamas.
I don't like the idea of BUYING something and then having my use of it monitored. That's no different than spyware.
Corporatism != Free Market
In case anyone else was trying to figure out these roles... (page 6 last two paragraphs - > page 7)
Veterans = The power gamers, deaths usually only environmental.
Solvers = Die often (mainly from falling), methodical, slow.
Pacifists = Cannon fodder basically.
Runners = They run, they die, they run. The first thing that comes to mind here is a player that goes for the flag immediately in CTF.
Every time I start to have faith in humanity, I ruin it by driving to work between 7 and 8 am.
What's the classification for the gamer who spends all of his time putting Laura in the crawling position and then getting a nice camera angle on the cleavage?
What? I own Tomb Raider Underworld and I wasn't informed my game behavior would be collected by some remote data mining app. I'm kinda shocked.
I guess that explains why the game would cut off any downloads on my Xbox while playing, which is something only multiplayer games normally do.
Welp, that's it. I kinda liked the demo for the new Batman game and was considering buying it, but I guess Eidos is even worse than I thought. I won't be giving them my money now.
The way you play games can change over time. I'm not always in the same mood when I play games, sometimes I like to goof off. Sometimes I like to just race around. If the game adapts to the way I was playing it will limit me the way I want to play the game.
Adaptive difficulty is better. If you have problem beating foo X, then after a while foo X will become easier. If you are stuck in a maze or unable to solve a puzzle, provide hints through game related mechanism (for example, receive a phone call with an hint, or let the PDA "compute" a solution).
There is a sword in the middle of the room, what would you like to do?
"Leave sword"
-Enemies Removed from all rooms-
-Puzzles added to all rooms-
You enter a room with a puzzle, what would you like to do?
"I hate puzzles!"
-Puzzles removed from all rooms-
-You Win! You are the new moon master!-
... to have it place you in a group, and then randomly select one of the other groups to place your gaming experience into. That way rather than giving you the experience most appropriate for your gaming style, it gives you a gaming experience that might actually cause you to approach the situation differently.
Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
it would be interesting if someone did this in an MMO like WOW, or EVE online
Its not my fault, someone put a wall in my way.
In the near future, such networks will be used to adapt games like Tomb Raider while they are played (e.g. by removing or adding puzzles and enemies), so you get the game you want.
This would only be possible in games that were similar enough to the previous title that the research could be applied.
For all the talk about 'neural' this and that, this is data. Data that was collected through hours of gameplay. Remove the data, and there's nothing to 'recognize'. No frame of reference.
It could be argued that all games are the same, but in reality they're not. A data point like 'deaths due to falling' wouldn't necessarily be as useful outside of Tomb Raider.
Now, for the sequel, sure. That would be useful. Then again, THAT isn't nearly new. Remember that psychic boss in Metal Gear who scanned your memory card? And that was what, seven-eight years ago?
Can you turn off the monitoring? I was going to buy it but won't if you can't avoid that.
...but how does it track when my 8-year-old daughter loads the disk and plays "Lara Croft: Monkey Chaser" ? I'm guessing they need a way to throw out that data, or else risk creating the new, bogus, player category of "Spastic Insomniac."
If only there was some mechanism by which they could collect this data before launching the game to the public. I'd call it an "alpha" release. I think I'll patent the concept...I'll be rich! ;)
From what I read of the paper, the research is not about a universal set of game play styles that can be applied to other games, but rather a method of automatically grouping players into different styles of game play given a particular game. They choose Tomb Raider as an example, not the data set to base all other games on. Yes it requires game play to be analyzed before hand, and yes, people have to name the groups, and yes, this is done per game.
When applied to enough games however, you may find similar groupings in every game with similar and dissimilar game play, but not necessarily, and I didn't read anything about this kind of assumption in the paper (I could have skimmed over it if it was there).
i rtfa and it didn't explain what these two play types were. at a guess, veterans are players who know exactly how to very quickly kill all NPC's and pacifists prefer to sneak past enemies (presumably looking for story progression more than combat).
i think this could be interesting as it would mean that various branches of game dev could all get an equal input and the player would define which aspects they get into more. obviously their goal is to increase player satisfaction and thereby recommendation sales (which are probably the most important if the impact of p2p downloading on music and video purchases is indicating). i personally HATE puzzles that aren't reasonably simple and present upfront as puzzles. the physics puzzles of hl2 were fine with me but i used walkthroughs on penumbra and tlj games because i am not good at puzzles.
i hadn't played much computer games for years between my late teens and late twenties, and what got me back into it was storyline - half life 2 has such a rich storyline, even if it is inane the acting is so well done. i suppose my early style was 'runner' as i just wanted to advance as quickly as possible to the next story element. then after a while i got to know how to play it better and not many incidents of dying and i started noticing side-tracks and objects and methods i hadn't tried before.
overall i think a more intelligent adaptation of the game would provide a deeper variation than weapon lethality, accuracy and the enemy's converse functions. replaying, for example, one wants ways to advance cutscenes faster, that would be something that a system like that could manage, to choose more curt versions of a dialogue sequence and determine triggers to advance and so forth. making enemies more alert or less alert to your presence in-game too, would require this kind of analysis, this would raise the challenge level for veteran players who would have to increase their response rate and vary tactics against npc's that are prepared sooner and move in more advanced tactical manouvres, varying between a bunch of idiotic disconnected enemies up to enemies that call each other over to attempt to fix and flank you.
one could go on and on. but overall this idea of games adapting play style to suit the player is going to mean more people like playing games, if this leads to a more fluid and individualised game experience this is a good thing because it also means if you want to try a different approach the game world responds differently to you and creates a different experience. it's a break from the ye olde railroad plot pathway and it can only make gaming better.
Okay, fine, but they already do this, don't they?
Does anyone know anything about the Ward Dendrogram shown in fig 3 on page 5? The T value seems arbitrary unless I misunderstand the text. Assuming the height differences between branches are indicative of distance between clusters, three or six groups would be more natural.
Was how they classified some of the players as "best". If you RTFA it says something along the lines of "The best player died x% from enemies" However, if you look at the percentages, that person must have died quite a few times in order to reach the 2 decimal place accuracy quoted. I would be much more inclined to believe a stat like "He died 10% from enemies" because it looks like the "best" gamer only died 10 times.
I realize this doesn't necessarily imply only 10 deaths, but at least there aren't 2 decimal points which imply quite a few more.
Do not argue with an idiot. He will drag you down to his level and beat you with experience.
In the near future, such networks will be used to adapt games like Tomb Raider while they are played (e.g. by removing or adding puzzles and enemies), so you get the game you want."
Awesome! In my case, I think it would be hilarious to watch Tomb Raider slowly morph into Starcraft.
If moderation could change anything, it would be illegal.
Valve does this as well. It creates some pretty interesting data, like the maps of where people die the most. It's easy to see how it can help designers.
When the paper says "The best player died only 6.32% of the times from opponents" I feel an urge to congratulate the player. Developers should do this type of deep analysis more often.
I hope the games will be forgetful and not lock themselves into a certain kind of play. In some kinds of games, I first run for the finish to experience the game and then crawl through the game again to discover the hidden corners. Or a visiting friend will play in a different way.
I think this is a fantastic idea and I hope more companies start doing it (provided they let you opt out, of course). I'm not really interested in the player profile aspect of it as much as the potential for balance/tweaking though.
For fighting games like Street Fighter IV etc, it's great because companies can use the data to help rebalance the characters. For example, if they notice that one character loses disproportionately to another, they can tweak the balance slightly in the next iteration (or even patch).
The ability to upload replays to the XBL/GFWL/PSN networks is also a great idea, because if the replay files are just a bit of metadata with stored inputs, game companies should be able to easily replay these games at high speed (by disabling audio/video) and capturing the resulting data.
At the end of the day, data is still king.
You could be a Veteran Solver. Someone who completes a level completely AND knows how not to fall into holes.
I think there are axes to this graph, and players can be any degree of the following:
1) Nimble - athletic control, precision of moment
2) Quester - Someone to explorers every possible puzzle/area/option
3) Aggressiveness - Avoid enemies? Shoot friendlies? Cope well in pvp?
4) Goal - Play for enjoyment or goal driven for completion? Pace of game.
the longer i played this game the more little teen girls kept showing up naked strutting around the levels for no apparent reason. soon i was interacting with them instead of dealing with enemies, solving puzzles, finishing levels or anything else. The more I interacted with them the younger they became. At some point there was a knock at the door followed by an arrest and seizure of my system. Before this was eventually ruled as entrapment, i had already served seven years of my ten year sentence for exhibiting potential sexual deviance. Although I was released early, my name was never removed from the sex offender list, neither were my children, nor my grandchildren.
most people who use 1984 as a knee-jerk reaction to anything they deem questionable haven't even read that book either.
Mark Rosewater, current head developer of Magic the Gathering, explained a much more in depth categorization. It has a lot more "gray areas" (in which people act like one or the other at different times), but I find it a lot better than this description (at least for tabletop games).
You can find the original article here. The other articles are found here and here/
Ginga no Rekshiya Mata Each page.
Do they make changes to games based on feedback from pre-release versions? Yes. Do they use that data to make versions of the game that are adaptable to the play style of the person playing the game? No.
Play kids games, watch video from popular kids shows, play free online games for kids, & more at Nick.com, Nickelodeon's online place for Kids! http://www.nick.com/
(No, this is NOT about cybering...)
I want to enjoy MMOs. I really do. But somehow I always wind up on the team with Leeroy @#$% Jenkins.
Someone REALLY needs to add this technology to an MMO -- and then help players to form groups with other people who have the same play style. Let Leeroy and his team of Runners go and have their fun. I'll hang out with some Puzzle-Solvers or Explorers or People Who Actually Read The Quest Dialog or whatever bucket is appropriate for the way I play the particular game. I need help joining the right pick-up group or guild or whatever (if I had social skills, I'd be outside) and an LFG Chat Channel isn't really enough.
THAT would be a customized game experience worth some money ($15/month to whoever could implement it).
-- 77IM
Student: Is it true that the foundation of the universe is paradox?
Master: Well, yes and no.
This is definitely the right way to go. I can't wait for the Fantasy Game
This sort of thing is useful in a games development context, i.e. helping developers understand how to build their game for a target audience. In every other context I can think of, it is at best futile and ignorant, at worst arrogant and immoral.
The paper introduces a methodology (via unsupervised learning) to player modeling using a large-scale dataset. Appropriate features might change from one game to another but the methodology is applicable to all games out there.
Not sure how Metal Gear was doing player modeling.
Myers-Briggs temperments broadly classify personalities into four categories based on how people perceive their surroundings and what motivates their behavior. It would be very interesting to see if the four classes of player they are observing also neatly fall into the sorting system of the Myers-Briggs model. If that proved to be true, then there would be a whole body of work game developers could use as the foundation for customizing player experiences.
...is unable to comment (yet).
I wonder when they will start outfitting little kids with monitors (implants, keyloggers, Trojaned webcams, Palm Pre's?) to find out if they are promising recruits to send to Battle School (ROTC?), and who they will eventually pick to fight the Buggers (drug lords, Islam, "ze Terrurists", anti-Capitalists?) for them.
The Hacker's Guide To The Kernel: Don't panic()!
The Tomb Raider game environments have been 3D from the beginning, and Tomb Raider: Underworld (TRU) is no exception. The game features exceptional graphics and takes full advantage of the graphics processors of game consoles.
Nice way to get free exposure via churnalism.
Oh, how convenient: a theory about God that doesn't involve looking through a telescope.
it's very annoying when people do that.
So ET was the perfect game! You may be right, even after 25 or so years, I still wake up in fear and sweat after having a nightmare about that game.