AIBattle

Distributed Agents (Swarms) Experiment

Total Battles Recorded: 253
Total Experience Gained: 17938845
Select Brains for Battle:

Human Brain:

Orc Brain:

Starting Army Sizes:



Edit Brain()


or Design a new brain:

new Brain Name:
Designer Name:
new Email:
password?
(Leave blank for a public read/write brain)





**Big thanks to Blizzard Entertainment**
(I used a couple WarCraft II sprite sets)

View Tutorial

How It Works


View Explorations



Program Brain in Workshop

Clone and Evolve existing Brain






Top 20 Brains
Name Designer [Exp] (W/L)
Tyler Tyler [4418502] (144/44)
Duncant Austin [3790698] (32/21)
Duncan Austin [2141558] (59/30)
Droopy Austin [1678574] (17/22)
Sally Austin [1593216] (33/7)
Larry Austin [836598] (5/0)
Vincent Austin [691962] (39/15)
Sherman Austin [617532] (86/30)
Newton Austin [559124] (31/14)
Eduardo Austin [458359] (61/18)
Willie Austin Griffith [228904] (9/1)
Heywood Zak Griffith [220900] (23/7)
Antoniov2 Austin [200675] (16/1)
Burrito Austin [131414] (32/13)
Antoniov4 Austin [102224] (8/1)
Max Austin [88544] (5/8)
DuncanD Duncan [40228] (3/5)
Guillermo britney [32029] (29/6)
Spreader Austin [27464] (13/0)
Doink Austin [20584] (0/1)
Recent Action:

Burrito wins (212 exp) from Scott
When: 2008-04-22 02:54:55
Where:

Burrito wins (424 exp) from Scott
When: 2008-04-22 02:53:37
Where:

Burrito wins (848 exp) from Scott
When: 2008-04-22 02:52:48
Where:

Droopy wins (3075.75 exp) from DumbHunter
When: 2008-04-22 02:52:27
Where:

Duncant wins (617532.5 exp) from Sherman
When: 2008-04-02 16:30:31
Where:

Duncant wins (40228 exp) from DuncanD
When: 2008-04-02 16:26:38
Where:

DuncanD wins (27463.5 exp) from Spreader
When: 2008-03-23 23:55:10
Where: Days

DuncanD wins (14490.5 exp) from DuncanD
When: 2008-03-23 23:43:26
Where: Days

DuncanD wins (2518.5 exp) from TX9
When: 2008-03-23 23:30:01
Where: Days

DuncanD wins (7173 exp) from DuncanD
When: 2008-03-23 23:17:25
Where: Days



About:

AIBattle is an ongoing attempt to create a good distributed war agent. A number of small agents are placed on a large world map with the goal of defending their castle and, ultimately, eliminating the enemy. Each agent has a very small sensor range and it is your job to design its very simple operating algorithm.

Game Play:

As the agents interact with their world, they gain experience for doing damage and killing other units (including sheep). As this experience increases, your agents become stronger and they upgrade to a Hero. Total team experience is also accumulated at the castle. As team experience increases, new units are created and released from the castle.

Observations:

Aggressive vs Defensive:
Brains that are programmed to be more aggressive tend to do better in situations where army sizes are small, such as brawls. (Think Lion) Brains that are highly defensive use their large numbers to provide safety. (Think Gazelle)

Grouping vs Wandering:
Brains that stay grouped survive much more often, but brains that wander tend to cover more ground and, therefore, discover the enemy castle quicker. Brains that force grouping seem to do better, but brains do group naturally because of similar motives.

Cooperation vs Individualism:
Brains seem to cooperate without any type of communication, but when they cooperate using shouts they can display more intelligent behavior by passing messages between each other. I think a good mix of both would work best.

Bored?

Click the 'Run Official Battle' link on the left and help us gather data by running a battle between a couple brains of your choice. Warning: it will probably kill your browser.




Created by: Austin Griffith