 |
How to improve the AI
This poll is closed. |
| Use of Planes |
   |
5 |
22.73% |
| Use of choppers |
   |
6 |
27.27% |
| Use of crawlers |
   |
16 |
72.73% |
| Forest-and-Forget/ Borehole strategies |
   |
17 |
77.27% |
| Naval unit use |
   |
6 |
27.27% |
| Focus/magnify units better |
   |
6 |
27.27% |
| Prioritize Build Queues correctly |
|
8 |
36.36% |
| Appropriate SE Choices vs Social setting |
|
10 |
45.45% |
| Use of Carriers/ Cloudbases |
|
4 |
18.18% |
| AA/ Probe Cruisers/ other unique units |
|
10 |
45.45% |
| Understand and react to terrain/ Planet |
|
8 |
36.36% |
| Concepts such as Super Science/ Hi Min cities |
|
9 |
40.91% |
| Mimicking human players |
|
10 |
45.45% |
| AI's must negotiate for xenobananas! |
|
7 |
31.82% |
| Other |
|
1 |
4.55% |
| Total: |
22 voters |
100% |
|
| |
|
|
Darsnan
|
 |
New Syracuse, Beta Prime
Dec 2001
time: 00:23
|
|
So what would be the things you'd most like improved in the AI's?
To detail what I mean by each of the options above:
1. Use of planes: the AI could use these so much better than they do now. Tactical strikes, bombing missions against terrain improvements, suicide missions, attacking when damaged, attacking to overwhelm (i.e. when its probable that 4-5 planes will be destroyed, but that in the long run more than 5 defenders in a base will be destroyed), etc.
2. Use of choppers: pretty much ditto from above, as well as flying them deep into enemy territories on suicide missions against Formers, Crawlers, etc.
3. Use of Crawlers: if I could only take Archaic's brain and transpose it into the AI, how they would then use crawlers!  Anyways, getting the AI's to use Crawlers more effectively, such as for heavy mineral cities, and for Super Science cities.
4. Forest-and-Forget/ Borehole strategy: Get those AI's to understand these winning concepts!
5. Naval unit use: The lessons of Operation Overlord were obviously lost on the AI's, so upgrade them from viking raiders/ pillagers into an effective triphibious assault force!
6. Focus/ Magnify AI's to attack one city/ area: all too often the AI's send units one, two, or three units at a time, only to be slaughtered over time by the hundreds by human players in carefully chosen defensive positions. But if the AI could collect a force, then launch a focalized assault, they could potentially overwhelm a human player's defensive position, or cause serious hardships/ challenges for the human player.
7. Prioritizing build queues correctly: AI's no longer building Hologram Theatres in cities that are under attack by enemy forces. AI's no longer building Tree Farms in cities that have no forest squares, etc...
8. Appropriate SE choices vs actual social setting: The AI should be able to understand that it should run FM and Wealth in peace, and Power while at war, and not the other way around....
9. Use of Carriers/ Cloudbases: The Carrier is the most powerful unit in the history of naval warfare, and Cloudbases, even though featured in the CBA SP Movie, didn't make th final cut in SMAC(X). So, simply put, teach the AI's to use these powerful units once they become available!
10. Anti-Aircraft/ Probe Cruisers/ other unique units: the AI's could be so much more difficult to defeat if they produced a few of these units.
11. AI understands and reacts to the terrain of Planet: if its 90% water, then go aquatic. If its 90 land, don't build battleships for 8 tile inland lakes. If its heavy fungus, tech beeline for worms/ Green SE, etc.
12. Concepts such as Super Science cities, Heavy Min cities: have the AI's identify likely candidates for Super Science cities (i.e. an "area" that is rich in energy) and build city enhancements in one city which will lead to a Super Science city, and identify candidate sites for high mineral cities for rush building SP's, units, etc.
13. Mimicking: the AI sees a human (or human players) aggragating units for an assault, and so does the same with its Best Weapon, Best Defender, Best Transport, Best etc for its own focalized attack. Also, if the AI sees human (or human players) grouping their SE choices for pro-peace, or pro-war, the AI mimics this as well (as a human player would if they had infiltration). If the AI sees a human's cities (or human players' cities) building either improvements or military units, it reacts accordingly.
14. AI's must negotiate for xenobananas! Well, duh, what with the market prices for xenobananas being at all-time highs! 
15. Other: tell me what you think is important for an improved AI!
D
Last edited by Darsnan on 27-05-2005 at 06:00
|
|
| |
|
| |
|
| |
|
|
|
Sikander
|
 |
Boulder, Colorado, United Snakes of America
Jan 2000
time: 22:23
|
|
A: I never had a problem against the AI in STW.
B: You can point an AI to victory, but you can't make them think. The game is simply too wickedly complex for the AI. Hell, we've spent several years deconstructing the game mechanics and potential tactics with large groups of intelligent people. What chance does the AI have when it is the same AI that shipped over 5 years ago?
There are two ways I can see to improve the AI. The easy way is to make this incredibly complicated game simpler (the Civ 3 approach). This has its limitations, but it could still be done much better than it was done in Civ 3 by having the human and the computer players play different games. The human would be playing a complex management game (as he does now) with a lot more nuance like personnel management, internal politics, local AI commanders rather than total tactical, strategic and political control etc. The AI would be there to do its best in more limited aspects of the game where the sheer number of factors can be significantly reduced in order to give its brute force approach a chance to pull a few surprises.
The alternative is an AI that improves over time, either alone or in conjunction with AI upgrades from the programmers. Perferably both. Every game could be uploaded to a server at Fireaxis for computer analysis. Fireaxians could troll the boards here and at CGN etc. for the latest tactics and could design countermeasures for their scripts. This of course would require an extensive investment over time for the company and probably some sort of fee for each iteration of the AI that is produced, but it also might be a blast.
|
|
| |
|
|
|
Darsnan
|
|
New Syracuse, Beta Prime
Dec 2001
time: 00:23
|
|
quote:
Originally posted by Kirov
Which reminds me of a question: when you create a predesigned unit, namely Probe Team with 0 movement, would AIs build them to protect their bases? |
The AI's would build them, but the units would still have movement points - no one has discovered yet how to disable movement points for units so that they are static.
quote:
Originally posted by Sikander
The alternative is an AI that improves over time, either alone or in conjunction with AI upgrades from the programmers. Perferably both. Every game could be uploaded to a server at Fireaxis for computer analysis. Fireaxians could troll the boards here and at CGN etc. for the latest tactics and could design countermeasures for their scripts. This of course would require an extensive investment over time for the company and probably some sort of fee for each iteration of the AI that is produced, but it also might be a blast. |
There are many significant variables involved in what you are describing, a few of which I'll list below:
1. MY in game: the MY is a variable and thus effects what viable tactics the AI should employ: a rush of infantry/ NL/ speeders will work exceptionally well before aircraft, OK after needlejets are employed, but would be massacred after choppers have entered the scene.
2. Each game is extremely individualistc in that it takes on the personality(s) of the individuals involved. Different players play the game differently, and so because of this one player may arrive at a point on a map at MY22XX, however how they arrived at that location can and probably will differ significantly from another player exposed to a similar environment. This then would make any "modelling" pretty much moot.
3. The physical makeup of Planet: 30% Ocean/ 50% Ocean/ or 70% Ocean? Combined with the shapes of the available landmasses. Combined with little rainfall/ moderate rainfall/ or heavy rainfall? Combined with little NL/ Average NL/ Heavy NL, combined with the mix of which human controlled Factions versus AI controlled Factions, etc.
All of these factors would also need to be taken into account as well, including initial placement of Factions upon landing on Planet. Very difficult to catalogue.
4. The learning curve of humans: human player x plays one way in a game. Player x matures over time. Player x encounters same circumstances in a new game. Player x employs new, learned strategies, against the AI.
5. AI/ Human relationships: can an AI comprehend the difference between a human desperate for an AI's support in a joint attack, versus a human's intent of committing an AI's forces to destruction, thus bleeding dry an AI's reserve in order for the human to attack it personally?
While ideally I understand the logic behind the argument, I can say empirically speaking that there are simply too many variables to ever see this idea through to fruition. It would take years to build the database described, and in the meantime the AI's continueally uploading the latest "best guess scenarios" would too often missfire, ending in ruined games for a lot of human players involved. And by the time the database would reach fruition (i.e. where the law of averages would really begin to take hold) the game would probably be on the way to becoming obsolete, if not already obsolete.
D
Last edited by Darsnan on 31-05-2005 at 07:29
|
|
| |
|
|
|
Sikander
|
|
Boulder, Colorado, United Snakes of America
Jan 2000
time: 22:23
|
|
quote:
Originally posted by Darsnan
The AI's would build them, but the units would still have movement points - no one has discovered yet how to disable movement points for units so that they are static.
There are many significant variables involved in what you are describing, a few of which I'll list below:
1. MY in game: the MY is a variable and thus effects what viable tactics the AI should employ: a rush of infantry/ NL/ speeders will work exceptionally well before aircraft, OK after needlejets are employed, but would be massacred after choppers have entered the scene.
2. Each game is extremely individualistc in that it takes on the personality(s) of the individuals involved. Different players play the game differently, and so because of this one player may arrive at a point on a map at MY22XX, however how they arrived at that location can and probably will differ significantly from another player exposed to a similar environment. This then would make any "modelling" pretty much moot.
3. The physical makeup of Planet: 30% Ocean/ 50% Ocean/ or 70% Ocean? Combined with the shapes of the available landmasses. Combined with little rainfall/ moderate rainfall/ or heavy rainfall? Combined with little NL/ Average NL/ Heavy NL, combined with the mix of which human controlled Factions versus AI controlled Factions, etc.
All of these factors would also need to be taken into account as well, including initial placement of Factions upon landing on Planet. Very difficult to catalogue.
4. The learning curve of humans: human player x plays one way in a game. Player x matures over time. Player x encounters same circumstances in a new game. Player x employs new, learned strategies, against the AI.
5. AI/ Human relationships: can an AI comprehend the difference between a human desperate for an AI's support in a joint attack, versus a human's intent of committing an AI's forces to destruction, thus bleeding dry an AI's reserve in order for the human to attack it personally?
While ideally I understand the logic behind the argument, I can say empirically speaking that there are simply too many variables to ever see this idea through to fruition. It would take years to build the database described, and in the meantime the AI's continueally uploading the latest "best guess scenarios" would too often missfire, ending in ruined games for a lot of human players involved. And by the time the database would reach fruition (i.e. where the law of averages would really begin to take hold) the game would probably be on the way to becoming obsolete, if not already obsolete.
D |
That's why it's the hard way. 
I still play the game on occasion against the current AI. Imagine how much better that experience would be if the programmers had tweaked the AI a little bit over time. I'm sure that some of us would be willing to fork over $10 or so in order to play against an AI which recognizes a few more tactics and strategies and can terraform better, ie things that modders are incapable of improving much because they are largely or entirely in the domain of the programmer. I can say confidently that I would have paid $10 a year in order to receive annual AI updates, the amount would have been trivial in comparison to the many hours of play that the game has given me.
As for the database of played games idea, the ideal would be a learning software that cranked away in the background analysing each player's game style (and altering tactics to meet it) with pre-chewed results being fed over the web to a larger database that the programmers could use to make larger changes to the AI algorithms. It is perhaps more science fiction than possibility currently, but it sure would be sweet.
Anyway, your points are quite valid and it certainly seems that simplifying the game is the option of choice for game companies. I hope that they do so with a lot more discretion than they did with Civ 3, which was dead on arrival as far as I was concerned. The simple truth is that in order to provide me with a complex and immersive environment that will keep me interested the game must be too complex for the AI to have a chance. The AI must play a different game than the human. It can work well playing a series of tactical mini-games against the human, but when it comes to complex systems like economics and diplomacy the AI is simply incapable of brute forcing its way into a serious competitor.
|
|
| |
|
|
|
binTravkin
|
 |
Lord of Progress of the Council of Lords of Gaia
Jan 2004
time: 07:23
|
|
quote:
Or you can just make the AI capable of learning from mistakes in the first place. |
As far as I know the universal algorithm of learning which works in a human mind has not yet been discovered for an AI.
Although we know the "see->save->see the same->use memory" sequence, computer just can't implement it in this simple way - it needs many things to be overlooked to even start saving things properly, not talking about using them on the correct circumstances.
We could, although tech AI some existing strategies and also remember good moves from the last games.
But the problem is that there are just too many variables to compare one game to other.
And eve if AI compares them both and say 99% of the variables match, the remaining 1% or even a single variable, no matter how much percent of the total it makes up can can change everything.
E.G. variable "enemy_has_nukes".
quote:
I'm sure that some of us would be willing to fork over $10 or so in order to play against an AI which recognizes a few more tactics and strategies and can terraform better, ie things that modders are incapable of improving much because they are largely or entirely in the domain of the programmer. I can say confidently that I would have paid $10 a year in order to receive annual AI updates, the amount would have been trivial in comparison to the many hours of play that the game has given me. |
A good "heads up"!
quote:
As for the database of played games idea, the ideal would be a learning software that cranked away in the background analysing each player's game style (and altering tactics to meet it) with pre-chewed results being fed over the web to a larger database that the programmers could use to make larger changes to the AI algorithms. It is perhaps more science fiction than possibility currently, but it sure would be sweet. |
And a brilliant idea about that database! It would be pretty hard to implement on a large scale, but such small tricks as "use AAA against chop&drop" or "bombard stacks" would help AI a lot together with the bonuses it already has!
|
|
| |
|
|
|
Commy
|
 |
St. Louis, MO, USA
Mar 2004
time: 05:23
|
|
Since SMAC is infinitely replayable, perhaps the AI should be tought to learn (sentient econometrics, anyone?)...
Okay, so lets say that every game you ICS, so on the first game, you kill the AI, then the AI learns some tricks about ICSing, and ICS itself, then by the third game, the AI has learned how to defeat ICSing with a certain military strategy, so on games to come, it will always know how to defeat someone ICSing...
Or, perhaps in every game, you attack the Hive first, so one the first game, you attack the Hive, they die...second game, you attack, and they put up a good fight, but still loose...third game, they attack you first and kill you...
Of course, not every game then would be a completely new game, because whatever you did in past games affects outcomes in future games...perhaps a "AI memory" reset button would be needed...
|
|
| |
|
|
|
Senethro
|
|
If you could invent an AI that could do that then you could buy Bill Gates.
How do you explain the concept of ICS to a CPU?
|
|
| |
|
|
|
Senethro
|
|
How would you tell the AI to spot ICS? Terraforming pattern? A certain ratio of bases/land area? Use of specialists and supply crawlers? I can think of plenty of exceptions.
|
|
| |
|
|
|
PJayTycy
|
|
You can have a "learning" AI only on some domains the developpers specify when creating it. For example your ICS: the AI should notice the close spacing of the bases. So, the developpers should have a variable "base_spacing" which the AI observes and reacts to. If nobody at Firaxis ever thought about ICS as a strategy, they would most likely not have inserted the means to track that. Likewise for something that could be called "num_crawlers_working"...
An AI can only learn by adjusting preset variables. But, already with the example I gave above, the difficulties come clear. If you win with an ICS aproach, the AI will value close base spacing and not use a lot of crawlers. If you win with a builder aproach, the opposite will happen.
So, it becomes clear there should be another variable, that can decides when to use ICS and when to use builder strategies (and then a set of values for each of these 2 strategies). We can see this now, after having played the game a lot. Probably the AI developpers see it too after playing the game a lot. But, when you as a player notice this, it's a lot easier to just implement both strategies than to make an AI who will discover them by himself.
Also, the AI can play very good, but still lose. Then it "learns" it played bad, and adjust its tactics for the next game. However, now it'll play worse. This game has only 1 critic (did you win or loose?) and an almost endless amount of variables to be adjusted, while only 10% of them really mattered in the just-played game.
|
|
| |
|
|
|
paramir
|
|
crawlers are most key
|
|
| |
|
|
|
paramir
|
|
[jk]says a morganite[/jk]
|
|
| |
|
|
|
Mead
|
|
quote:
Originally posted by Darsnan
So what would be the things you'd most like improved in the AI's?
To detail what I mean by each of the options above:
***
9. Use of Carriers/ Cloudbases: The Carrier is the most powerful unit in the history of naval warfare, and Cloudbases, even though featured in the CBA SP Movie, didn't make th final cut in SMAC(X). So, simply put, teach the AI's to use these powerful units once they become available!
***
D |
D
I agree with just about all of your suggestions. It looks like a nice compiliation of the complaints many here have had about AI limitations.
Suggestion 9 got my attention. The few times I have made A/C carriers I lost them, with all the A/C on board, whenever they got in range (and detected) of the missile equipped AI. Even with a large number of SAM A/C included, and escorted by SAM well armoured ships I still lost my carrier task forces.
Mead
PS
I guess it would be more useful to only send them in range to do their strike then retire out of range, but even better was to rely on the normal get a foothold (via conquest, probe, or Needlejet CP new base) near the AI and launch my chop and drop from there.
|
|
| |
|
| |
All times are GMT. The time now is 05:23.
Apolyton Time is 00:23. |
top of page
|
|
|
Forum Rules:
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts
|
HTML code is ON
vB code is ON
Smilies are ON
[IMG] code is ON
|
|
|
|
|
|
27-05-2005 05:47
I've even given the alien AI's free nerve gas, and they still can't really take advantage of it the way they should (although it is interesting to see them getting the "+50% Nerve Gas Attack" when using a nuke! 
|