Category Archives: Scenarios

Feeding the Machine

The famous Turing Machine¹⁾It was first described in Turing’s, “On Computing Machines with an Application to the Entscheidungsproblem,” in 1937 which can be downloaded here: https://www.cs.virginia.edu/~robins/Turing_Paper_1936.pdf. Also a very good book on the subject is Charles Petzold’s, “The Annotated Turing: A Guided Tour through Alan Turing’s Historic Paper on Computability and the Turing Machine.” was a thought experiment and, until recently did not physically exist ²⁾Yes, somebody has built one and you can see what Turing described here: https://www.youtube.com/watch?v=E3keLeMwfHY . When computer scientists talk about machines we don’t mean the, “lumps of silicon that we use to heat our offices,” (thanks Mike Morton for this wonderful quote), but, rather, we mean the software programs that actually do the computing. When we talk about Machine Learning we don’t think that the physical hardware actually learns anything. This is because, as Alan Turing demonstrated in the above paper, the software functions as a virtual machine; albeit, much more efficiently than creating a contraption with pens, gears, rotors and an infinitely long paper strip.

When I talk about, “feeding the machine,” I mean giving the program (the AI for General Staff is called MATE: Machine Analysis of Tactical Environments and the initial research was funded by DARPA) more data to learn from. Yesterday, the subject at machine learning school was Quatre Bras.

Screen shot of the General Staff AI Editor after analysis of Quatre Bras and calculating the flanking Schwerpunkt or point of attack (blue square). Click to enlarge.

The MATE tactical AI algorithms produce a plan of attack around a geographic point on the battlefield that has been calculated and tagged as the Schwerpunkt, or point where maximum effort is to be applied. In the above (Quatre Bras) scenario the point of attack is the extreme left flank of the Anglo-Allied (Red) army. I apply the ‘reasonableness test’ ³⁾Thank you Dennis Beranek for introducing me to the concept of ‘reasonableness test’. See https://www.general-staff.com/schwerpunkt/ for explanation and think, “Yes, this looks like a very reasonable plan of attack – a flanking maneuver on the opponent’s unanchored left flank – and, in fact, is a better plan than what Marhshal Ney actually executed.

It would be good at this point to step back and talk about the differences in ‘supervised’ and ‘unsupervised’ machine learning and how they work.

Supervised machine learning employs training methods. A classic example of supervised learning is the Netflix (or any other TV app’s) movie recommendations. You’re the trainer. Every time you pick a movie you train the system to your likes and dislikes. I don’t know if Netflix’s, or any of the others, use a weighting for how long (what percentage watched over total length of show) watched but that would be a good metric to add in, too. Anyway, that’s how those suggestions get flashed up on the screen: “Because you watched Das Boot you’ll love The Sound of Music!” Well, yeah, they both got swastikas in them, so… ⁴⁾Part of the problem with Netflix’s system is that they hire out of work scriptwriters to tag each movie with a number of descriptive phrases. Correctly categorizing movies is more complex than this.

Supervised machine learning uses templates and reinforcement. The more the user picks this thing the more the user gets this thing. MATE is unsupervised machine learning. It doesn’t care how often a user does something, it cares about always making an optimal decision within an environment that it can compare to previously observed situations. Furthermore, MATE is a series of algorithms that I wrote and that I adjust after seeing how they react to new scenarios. For example, in the above Quatre Bras scenario, MATE originally suggested an attack on Red’s right-flank. This recommendation was probably influenced by the isolated Red infantry unit (1st Netherlands Brigade) in the Bois de Bossu woods. After seeing this I added a series of hierarchical priorities with, “a flank attack in a woods (or swamp) is not as optimal as an attack on an exposed flank with clear terrain,” as a higher importance than pouncing on an isolated unit. And so I, the designer, learn and MATE learns.

My main concern is that MATE must be able to ‘take care of itself’ out there, ‘in the wild’, and make optimal decisions when presented with previously unseen tactical situations. This is not writing an AI for a specific battle. This is a general purpose AI and it is much more difficult to write than a battle specific AI. One of the key aspects of the General Staff Wargaming System is that users can create new armies, maps and scenarios. MATE must make good decisions in unusual circumstances.

Previously, I have shown MATE’s analysis of 1st Bull Run and Antietam. Below is the battle of Little Bighorn in the General Staff AI Editor:

The battle of Little Bighorn in the General Staff AI Editor. Normally the MATE AI would decline to attack. However, when ordered to attack, this is MATE’s optimal plan. Click to enlarge.

I would like to expose MATE to at least thirty different tactical situations before releasing the General Staff Wargame. This is a slow process. Thanks to Glenn Frank Drover of Forbidden Games, Inc. for donating the superb Quatre Bras map. He also gave us maps for Ligny and Waterloo which will be the next two scenarios submitted to MATE. We still have a way to go to get up to thirty. If anybody is interested in helping to create more scenarios please contact me directly.

References[+]

References
↑1	It was first described in Turing’s, “On Computing Machines with an Application to the Entscheidungsproblem,” in 1937 which can be downloaded here: https://www.cs.virginia.edu/~robins/Turing_Paper_1936.pdf. Also a very good book on the subject is Charles Petzold’s, “The Annotated Turing: A Guided Tour through Alan Turing’s Historic Paper on Computability and the Turing Machine.”
↑2	Yes, somebody has built one and you can see what Turing described here: https://www.youtube.com/watch?v=E3keLeMwfHY
↑3	Thank you Dennis Beranek for introducing me to the concept of ‘reasonableness test’. See https://www.general-staff.com/schwerpunkt/ for explanation
↑4	Part of the problem with Netflix’s system is that they hire out of work scriptwriters to tag each movie with a number of descriptive phrases. Correctly categorizing movies is more complex than this.

Thank You Wargaming Community!

5 Replies

Last week I posted an appeal to the wargaming community and backers of The General Staff Wargaming System that I needed more maps and Orders of Battle (OOBs). The General Staff Wargaming System is designed to handle any conflict in the Black Powder era and the machine learning AI needs as much input as possible.

The five layers that make up a General Staff map.

The General Staff Army Editor makes it pretty easy to create four of the five layers of a map file (see above). The problem is the beautiful background image that the user sees on screen (the computer AI couldn’t care less about the visual map). I’ve been able to locate a lot of great maps; especially from the American Civil War and the US Library of Congress but we still need more.

Waterloo from Glenn Drover (Forbidden Games) and Jared Blando. Click to enlarge.

A couple of days ago I received an email from the famous game designer, Glenn Drover (Forbidden Games), who offered us the use of three maps that he had researched and were drawn by artist Jared Blando. Here’s a link to Forbidden Games’ site. Please check out their fantastic board games!

Ligny from Glenn Drover (Forbidden Games) and Jared Blando. Click to enlarge.

The three battlefield maps were Waterloo, Ligny and Quatre Bras.

Quatre Bras from Glenn Drover (Forbidden Games) and Jared Blando. Click to enlarge.

What is especially amazing is how well these three maps fit the style that I’ve wanted to create for General Staff.

In addition to these three great maps, which we will definitely be using for the battles of Waterloo, Ligny and Quatre Bras, I’ve received emails from a number of other wargamers who have offered to research OOBs; especially some in another language.

I am completely blown away (I know it’s a cliche, but I don’t have any other words) by the kindness and generosity shown me by the wargaming community. Thank you very much!

Maps, Commanders & Computers

3 Replies

How a map of the battle of Antietam looks to us humans. Screen shot from the General Staff Map Editor. Click to enlarge.

How the computer sees the same map (terrain and elevation). This is actually a screen shot from the Map Editor with the ‘terrain’ and ‘elevation’ layers turned on. Click to enlarge.

Computer vision is the term that we use to describe the process by which a computer ‘sees'¹⁾When describing various AI processes I often use words like ‘see,’ ‘understand,’ and ‘know’ but this should not be taken literally. The last thing I want to do is to get in to a philosophic discussion on computers being sentient. the world in which it operates. Many companies are spending vast sums of money developing driverless or self-driving cars. However, these AI controlled cars have had a number of accidents including four that have resulted in human fatalities.²⁾https://en.wikipedia.org/wiki/List_of_self-driving_car_fatalities The problem with these systems is not in the AI – anybody who has played a game with simulated traffic (LA Noir, Grand Theft Auto, etc.) knows that. Instead, the problem is with the ‘computer vision’; the system that describes the ‘world view’ in which the AI operates. In one fatality, for example, the computer vision failed to distinguish a white semi tractor trailer from the sky.³⁾https://www.theguardian.com/technology/2016/jun/30/tesla-autopilot-death-self-driving-car-elon-musk Consequently, the AI did not ‘know’ there was a semi directly in front of it.

In my doctoral research I created a system by which a program could ‘read’ and ‘understand’ a battlefield map⁴⁾TIGER: An Unsupervised Machine Learning Tactical Inference Generator http://www.riverviewai.com/download/SidranThesis.html. This is the system that we use in General Staff.

The two images, above, show the difference in how a human commander and a computer ‘see’ the same battlefield. In the top image the woods, the hills and the roads are all obvious to us humans.

The bottom, or ‘computer vision’ image, is a bit of a cheat because this is how the computer information is visually displayed to the human designer in the General Staff Map Editor. The bottom image is created from four map layers (any of which can be displayed or turned off):

The four layers that make up a General Staff map.

The background image layer in a General Staff map is the beautiful artwork shown in the top image. The place names and Victory Points layer are also displayed in the top image. The terrain and elevation layers are described below:

The next three images are actual visual representations of the contents of memory where these terrain values are stored (this is built in to the General Staff Map Editor as a debugging tool):

Screen shot from the Map Editor showing just terrain labeled as ‘water’. Click to enlarge

Screen shot from the General Staff Map Editor showing the terrain labeled as ‘woods’. Click to enlarge.

Screen shot from the General Staff Map Editor showing the terrain labeled ‘road’. Click to enlarge.

A heightmap for Antietam. This is a visual representation of elevation in meters (darker = lower, lighter = higher). Click to enlarge.

To computers, an image is a two-dimensional array; like a giant tic-tac-toe or chess board. Every square (or cell) in that board contains a value called the RGB (Red, Green, Blue⁵⁾Except in France where it’s RVB for Rouge, Vert, Bleu ) value. Colors are described by their RGB value (white, for example, is 255,255,255). If you find this interesting, here is a link to an interactive RGB chart. General Staff uses a similar system except instead of the RGB system each cell contains a value that represents various terrain types (road, forest, swamp, etc.) and another, identical, two-dimensional array, contains values that represent the elevation in meters. To make matters just a little bit more confusing, computer arrays are actually not two-dimensional (or three-dimensional or n-dimensional) but rather a contiguous block of memory addresses. So, the terrain and elevation arrays in General Staff which appear to be two-dimensional arrays of 1155 x 805 cells are actually just 929,775 bytes long hunks of contiguous memory. To put things in perspective, just those two arrays consume more RAM than was available for everything in the original computer systems (Apple //e, Apple IIGS, Atari ST, MS DOS, Macintosh and Amiga) that I originally wrote UMS for.

So, not surprisingly, a computer stores its map of the world in which it operates as a series of numbers ⁶⁾Yes, at the lowest level the numbers are just 1s and 0s but we’ll cover that before the midterm exams. that represent terrain and elevation. But, how does a human commander read a map? I posed this question to Ben Davis, a neuroscientist and wargamer, and he suggested looking at a couple of studies. In one article⁷⁾https://www.citylab.com/design/2014/11/how-to-make-a-better-map-according-to-science/382898/, Amy Lobben, head of the Department of Geography at the University of Oregon, said, “…some people process spatial information egocentrically, meaning they understand their environment as it relates to them from a given perspective. Others navigate more allocentrically, meaning they look at how other objects in the environment relate to each other, regardless of their perspective. These preferences are linked to different regions of the brain.” Another⁸⁾https://www.researchgate.net/publication/251187268_USING_fMRI_IN_CARTOGRAPHIC_RESEARCH reports the results of fMRI scans while, “subjects perform[ed] navigational map tasks on a computer and again while they were being scanned in a magnetic resonance imaging machine.” to identify specific, “involvement or non-involvement of the brain area.. doing the task.”

So, how computers and human commanders read and process maps is quite different. But, at the end of the day, computers are just manipulating numbers following a series of algorithms. I have written extensively about the algorithms that I have developed including:

“Algorithms for Generating Attribute Values for the Classification of Tactical Situations.”
“Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.”
“Good Decisions Under Fire: Human-Level Strategic and Tactical Artificial Intelligence in Real-World Three-Dimensional Environments.”
“Current Methods to Create Human-Level Artificial Intelligence in Computer Simulations and Wargames”
Human Level Artificial Intelligence for Computer Simulations and Wargames.
An Analysis of Dimdal’s (ex-Jonsson’s) ‘An Optimal Pathfinder for Vehicles in Real-World Terrain Maps’

These papers, and others, can be freely downloaded from my web site here.

As always, please feel free to contact me directly if you have any questions or comments.

References[+]

References
↑1	When describing various AI processes I often use words like ‘see,’ ‘understand,’ and ‘know’ but this should not be taken literally. The last thing I want to do is to get in to a philosophic discussion on computers being sentient.
↑2	https://en.wikipedia.org/wiki/List_of_self-driving_car_fatalities
↑3	https://www.theguardian.com/technology/2016/jun/30/tesla-autopilot-death-self-driving-car-elon-musk
↑4	TIGER: An Unsupervised Machine Learning Tactical Inference Generator http://www.riverviewai.com/download/SidranThesis.html
↑5	Except in France where it’s RVB for Rouge, Vert, Bleu
↑6	Yes, at the lowest level the numbers are just 1s and 0s but we’ll cover that before the midterm exams.
↑7	https://www.citylab.com/design/2014/11/how-to-make-a-better-map-according-to-science/382898/
↑8	https://www.researchgate.net/publication/251187268_USING_fMRI_IN_CARTOGRAPHIC_RESEARCH

“What Ifs” at Little Bighorn

9 Replies

I‘m used to learning a lot when researching a battle but nothing prepared me for the ‘what ifs’ of Little Bighorn. My doctorate is in computer science but I have been an American Civil War buff since I was about five years old. I’m very familiar with brevet Major General George Armstrong Custer’s achievements during the Appomattox campaign where he commanded a division that smashed Pickett’s right flank at Five Forks. I knew that after the war Custer returned to his previous rank in the U. S. Army of Lt. Colonel, that he fell under a cloud with U. S. Grant, was stripped of his command, and had to beg for it back from President Grant, himself, at the White House.

Brevet Major General George Armstrong Custer taken May 1865. Credit: Civil war photographs, 1861-1865, Library of Congress, Prints and Photographs Division. Click to enlarge.

And, of course, I knew of the debacle at the Little Bighorn.

After I wrote UMS, the first computer wargame construction system, users began to send me Little Bighorn scenarios that included Gatling guns. I assumed that these were science fiction ‘what if’ scenarios. such as a story I read back in the ’60s about what if Civil War units had automatic weapons from the future. But, recently, while reading Stephen Ambrose’s Crazy Horse and Custer I learned that General Alfred Terry, Custer’s superior and the commander of the expedition, had indeed offered Custer not just three Gatling Guns (manned by troops from the 20th Infantry ¹⁾The Guns Custer Left Behind; Historynet
https://www.historynet.com/guns-custer-left-behind-burden.htm ) but four extra troops from the 2nd U. S. Cavalry. Custer turned down Terry’s offer of reinforcements and more firepower with these infamous words:

“The Seventh can handle anything it meets.” – Custer to Terry

Photo taken by F. Jay Haynes of one of the Gatling guns that were available to the 7th Cavalry. Click to enlarge.

Screen capture of the Order of Battle of the 7th US Cavalry with the addition of 3 Gatling guns and 4 companies of the 2nd US Cavalry. Click to enlarge.

As for the battle of Little Bighorn, itself, I didn’t know much more than the broad outline that Custer and his command were killed to the last man by an overwhelming number of Native American warriors (this, of course, wasn’t correct as members of Reno’s and Benteen’s columns survived). Custer, himself, was the text book image of hubris and became the butt of late night comedians and humorous pop songs. But the reality turned out to be much more complex and nuanced.

Custer had a reputation of being dashing, headstrong, and gallant; the iconic description of a cavalry commander. The traditional narrative of the disastrous battle of Little Bighorn is that Custer impulsively attacked a vastly superior enemy force; possibly propelled by a belief that Native American warriors were no match for organized cavalry armed with 45-70 trap door carbines. Indeed, Napoleon’s maxim was that, “twenty or more European soldiers armed with the best weapons could take on fifty or even a hundred natives, because of European discipline, training and fire control.” ²⁾“Crazy Horse and Custer” p. 425 Stephen Ambrose To make matters worse, Custer had pushed the 7th mercilessly and by the time they arrived at the battlefield both men and horses were exhausted.

Custer’s plan of attack is also widely condemned as overly optimistic. He split his command of 616 officers and enlisted men of the 7th cavalry into three battalions. If the four companies of 2nd Cavalry had come along, Custer’s force would be 30% larger.³⁾Ibid The main force led by himself would be the right flanking column, Reno would have the left flanking attack column and Benteen and the pack train would be in the middle. Custer also drastically underestimated the Native American force at about 1,500.

In theory, Custer’s plan of attack wasn’t that bad:

If Custer was up against a force that was only two or three times his size and
If Reno had pressed home his attack drawing the Native American warriors east toward him and
If Custer had been able to cross the Little Bighorn above the Native American camp and
If Custer had been able to attack the village while the warriors were engaged with Reno

Custer might have, indeed, had a great victory that would have propelled him to the US Presidency (as he had hoped). But none of these suppositions were correct.

Screen shot of the General Staff Scenario Editor where the battle of Little Bighorn scenario is being set up. Not the Order of Battle of the 7th Cavalry (with attached units of the 2nd Cavalry and Gatling guns) on the left. Units are positioned by clicking and dragging them from the Order of Battle Table on the left onto the map. Click to enlarge.

So, the question remains: what value for Leadership would you give to Custer?

Screen shot of the General Staff Army Editor showing the slider that sets the Leadership value for a commander. What value would you give Custer? Click to enlarge

By the way, there will be three separate Little Bighorn scenarios for the General Staff Wargaming System: historically accurate Order of Battle for the 7th Cavalry, the 7th Cavalry plus four companies of the 2nd US Cavalry and 7th Cavalry plus four companies of the 2nd US Cavalry and 3 Gatling guns.

References[+]

References
↑1	The Guns Custer Left Behind; Historynet https://www.historynet.com/guns-custer-left-behind-burden.htm
↑2	“Crazy Horse and Custer” p. 425 Stephen Ambrose
↑3	Ibid

Free Scenarios Twenty-One Through Twenty-Five