.com.unity Forums - AI DEATH MATCH 2

.com.unity Forums (http://forum.shrapnelgames.com/index.php)

- Space Empires: IV & V (http://forum.shrapnelgames.com/forumdisplay.php?f=20)

- - AI DEATH MATCH 2 (http://forum.shrapnelgames.com/showthread.php?t=8617)

Re: AI DEATH MATCH 2

[quote]Originally posted by Tymy:

Quote:

Hi CyberSol,
I�d like to see an area in the middle of the map wich is NOT connected by Warppoints. Let�s say that this area will be about 25% of the total space.

I will be making the map with all warp points connected to test the AI's in general expansion and combat. However, once you have the map I'm making (which is derived from MB's), it is very easy to load it in the map maker and delete both sides of the six warp points that connect the 3 middle systems of the dueling channels. The warp points are much easier to delete than add in the included editor.

Re: AI DEATH MATCH 2

Quote:

Originally posted by cybersol:
Wow, its been a great second death match. I have read every post in both death match threads.

I downloaded both maps and they are great at balancing things for all atmosphere and colony types. I also like the three dualing channels with the asteroid systems seperating the two sides.

But considering the differences we have seen in this death match between starting in the upper or lower side, I thought there might be a way to further balance the two halves. I am currently working to change the map to incorporate two new ideas. The first idea is that the same planet types and number should be the same distance in game hexes (not systems) from the starting planets for both empires. The second idea is symmetry. If you consider the entire galaxy map with all the system maps inside and do a 180 degree rotation, then the map falls back on top of itself. Player two and three swapped sides during the rotation, but the map (even system maps) look exactly the same as before the rotation. Thus the two players start in absolutely identical situtations.

I am about 3/4 of the way through adding these concepts to your map, but I wanted to know your opinion. Also, what other map changes have considered making but not implemented? Thanks.

I really like your idea! Please post the map when you could have it!
About the difference to start in the upper or lower side... I don't know why, but the "Colony Ship Bug" always happen in the upper side.
Don't know why an AI decide to build only "Colony Gas" ships, when have lots of Ice planets available to colonize.

Re: AI DEATH MATCH 2

Quote:

Originally posted by Tymy:
<blockquote>quote:<hr />Originally posted by cybersol:
Wow, its been a great second death match. I have read every post in both death match threads.

I downloaded both maps and they are great at balancing things for all atmosphere and colony types. I also like the three dualing channels with the asteroid systems seperating the two sides.

But considering the differences we have seen in this death match between starting in the upper or lower side, I thought there might be a way to further balance the two halves. I am currently working to change the map to incorporate two new ideas. The first idea is that the same planet types and number should be the same distance in game hexes (not systems) from the starting planets for both empires. The second idea is symmetry. If you consider the entire galaxy map with all the system maps inside and do a 180 degree rotation, then the map falls back on top of itself. Player two and three swapped sides during the rotation, but the map (even system maps) look exactly the same as before the rotation. Thus the two players start in absolutely identical situtations.

I am about 3/4 of the way through adding these concepts to your map, but I wanted to know your opinion. Also, what other map changes have considered making but not implemented? Thanks.

Hi SyberSol,

I like your idea. A good balanced map will force the ai to its limits. I�d like to see an area in the middle of the map wich is NOT connected by Warppoints. Let�s say that this area will be about 25% of the total space.

This means that the only way to make first contact is to go around this area. To challenge the ai even further more you can make a corridor to both empires by a couple of systems wich are connected by warppoints with a damage when passing through.

Make the ai to do some work to make first contact and even more work to establih a position �on the otherside�.

Just my thoughts !

gr. Tymy<hr /></blockquote>Hugh soory Tymy... but I'm with Unknown Enemy here.
With your suggestion, I think the test would be very partial. Also, even the current map is partial: many times an AI start at the side of other AI...

Re: AI DEATH MATCH 2

Tessellate vs United Flora.

The Tessellate ressisted during a time, but when the UF sent their first strong fleets, the game was over.
The UF won at the turn 250.

Here the link: Tessellate_vs_UFlora_FinalB.zip

Re: AI DEATH MATCH 2

United floras 2
Tesselate 1

Re: AI DEATH MATCH 2

United Flora vs Tessellate.

The United Flora won at the turn 310.
A fairly fast victory, considering that they started at the upper side... and looks like the predictions about who would win this final, are accurated.

Here the link: UFlora_vs_Tessellate_Finalb.zip

Edit: standings

United Flora 3
Tessellate 1

[ May 23, 2003, 00:17: Message edited by: Master Belisarius ]

Re: AI DEATH MATCH 2

hmm, this is almost like a tennis match. Starting on the upper or lower side giving you an advantage. If that is so, the UF are one 'break' ahead http://forum.shrapnelgames.com/images/icons/icon7.gif .

Rollo

Re: AI DEATH MATCH 2

Quote:

Originally posted by Rollo:
hmm, this is almost like a tennis match. Starting on the upper or lower side giving you an advantage. If that is so, the UF are one 'break' ahead http://forum.shrapnelgames.com/images/icons/icon7.gif .

Rollo

hehehehe, from a long time ago, I had the same thought! http://forum.shrapnelgames.com/images/icons/icon7.gif
By the way, the UF won the game that was running during the night... and they're now 4-1.

Re: AI DEATH MATCH 2

Quote:

... and looks like the predictions about who would win this final, are accurated.

I'm not counting any chickens until they hatch http://forum.shrapnelgames.com/images/icons/icon12.gif

MB, thanks again for doing this death match for us! If I recall correctly, this thread identified at least one bug (the colony bug), and brought up at least 3 or 4 Posts about (distinct) methods for (re)designing AIs. I'd call that a great success.

Re: AI DEATH MATCH 2

Thanks for the encouragement. I have finally finished the new map I have been working on. This map is based on the system layout of Master Belisarius's Death Match 2 map, but each system map has been completely reworked.

Map Use: To use put a observer as player one in the far away Zitrod system with no warp points, put AI Oppenent 1 as player two in the upper central Aldan system, and AI Opponent 2 as player three in the lower central Sutran system. Change the planet type and atmosphere to match the each players starting colony and atmosphere preferences. If you fail to do this, then some players will get additional planets that ruin the movement point and planet type balance of the map.

Goals/Changes:

A) Balance of planet type and atmosphere changed to be movement point based instead of number of systems away based.
Example: If there is a nice mineral rich rock oxygen planet 8 movement points away from the nearest home planet, then there are also nice mineral rich ANY ANY planets 8 movement points away.

B) Make the overall map symmetric to 180 degree rotation. If you picture the galaxy map and each system map inside and rotate 180 degrees about the central system between the AI opponents, then the resulting galaxy map and each system map looks identical. The AI opponents starting positions have switched sides and the human player now observes from far away on the other side, but the position of objects within the systems looks the same.
Example: If AI opponent one enters a system and turns left to find a nice juicy mineral rich ice methane planet, then AI opponent 2 can enter the equivalent system on his side of the map and turn left and find a mineral rich ice methane planet of the same juicyness.

C) Closely balance total number of facilities available for each planet type and atmosphere so the AI's are on a similar footing. There are 5 medium rock and ice planets, one of each atmosphere in every system. There are also 4 large gas planets, one of each valid atmosphere. Finally there is a tiny rock none and ice none moon like planet in each system. This gives 32 facilities per system (fps) for gas giant players and rock/ice none players, but only 28 fps for rock/ice other atmospheres. There are seven total systems on each players side so that is a 28 facility disadvantage for rock/ice other atmospheres types. So for more facility balance, 4 additional medium rock and 4 additional medium ice planets were added among the seven systems (all the average distance away with the average quality). Now rock/ice other atmospheres have 31.4 fps, gas other have 32.0, and rock/ice none have 33.7 fps. Gas player have to colonize the fewest planets for the same number of facilities while rock/ice none have to colonize the most planets. I think the overall result is closely balance, with slight biases in the same direction as they would be on random maps.

D) Add some variety in planet qualities while maintaining balance. Among the 7 systems near each player are seven types of balanced planet sets:
Planet Type, Mineral Value, Organic Value, Radioactive Value
1, 115, 115, 115
2, 30, 95, 140
3, 95, 140, 30
4, 140, 30, 95
5, 30, 30, 70
6, 30, 70, 30
7, 95, 30, 30
Type 1 planets are all in the single system away from the opponent, while type 2-4 planets are distributed among the three closest systems toward the opponent, and type 5-7 systems are distributed among the three second closet systems toward the opponent. The distribution occurs like this: rock type 2, ice type 3, and gas type 4 are in one system; then ice type 2, gas type 3, and rock type 4 are in another; and finally gas type 2, rock type 3, and ice type 4 are in the Last of the set.

E) Changed the system names so player 2(3)'s home system starts with A(S), those one away start with B(T), and two away start with D(X). The middle asteroid systems start with M.

AI Dueling Map

[ May 23, 2003, 21:36: Message edited by: cybersol ]