Category Archives: Algorithm

A Human-Level Intelligence at Antietam

“Map of the battlefield of Antietam,” by William H. Willcox. Published in Philadelphia. Lithograph of P. S. Duval and Son, 1862. From the US Library of Congress.

There are many reasons that I am intensely interested in this particular American Civil War battle fought on less than twenty square miles wedged in between the Potomac River and Antietam Creek. The battle of Antietam (September 17, 1862) exhibits a number of significant battlefield attributes which I use as base line cases to test algorithms used in creating a human-level tactical artificial intelligence ¹⁾MATE: Machine Analysis of Tactical Environments. Specifically, Antietam definitively demonstrates ²⁾see http://riverviewai.com/download/SidranThesis.pdf the following attributes:

Choke Points
Anchored Flank
Interior lines of communication
Exterior lines of communication
Restricted Avenue of Retreat
Restricted Avenues of Attack

For example, in a blind survey of Subject Matter Experts (SMEs), it was overwhelmingly agreed that the RED (Confederate) left flank at the battle of Antietam exhibited the attribute of ‘anchored flank‘ ³⁾a flank that is attached to or protected by terrain, a body of water, or defended fortifications. and other positions, such as RED’s (Russian and Austrian) left flank at Austerlitz SMEs overwhelmingly agreed that the flanks do not exhibit the attribute of ‘anchored’ and are, therefore, unanchored. Once we have an example of an anchored flank and another example of an unanchored flank we can begin testing algorithms to detect the attribute of an anchored flank.

In my doctoral thesis (above) I demonstrated the algorithm ⁴⁾see pages 45-6 http://riverviewai.com/download/SidranThesis.pdf for detecting the attribute of anchored and unanchored flanks. I have made a number of substantial improvements to the original algorithm since then which are now incorporated into the current MATE.

We have recently posted analyses of other battles that did not exhibit the attribute of an anchored flank (Ligny and 1st Bull Run, or Manassas). MATE correctly recognized that Ligny and Manassas do not have these attributes.

The tactical situation for Blue at Antietam is quite different than Blue’s positions at Ligny and Manassas (is it not curious how often Blue is the attacker in wargames?). The key difference, of course, is the lack of an open flank to attack. MATE will always attack an open flank if it can. Without an obvious objective, like an exposed flank, MATE will next look at opportunities to fulfill victory conditions. For Antietam, as Blue, MATE sees the situation like this:

MATE Analysis of Antietam from the Blue position. Screen shot. Click to enlarge.

Below is a list of statements, predicates and conclusions generated by MATE during the above analysis with my commentary added on the right:

MATE analysis of Antietam. Click to enlarge.

I recently added a set of algorithms that recognize the composition of battle groups and exploits any possible advantages. For example:

Screen shot showing MATE analysis of BLUE position at Ligny. NB: Battle Group #3 (Pajol’s and Exelmans’ cavalry divisions) are, “snatching the pawn,” at Balatre. Click to enlarge.

At Ligny, above, MATE has recognized that Battle Group #3 and Battle Group #4 are uniquely cavalry (and horse artillery) battle groups and are to be used differently. While Battle Group #4 is held in reserve, Battle Group #3 will snatch Balatre. Though it is valued at only 10 Victory Points, MATE realized that no enemy force could oppose it. That said, I can still hear the voice of my old chess tutor, Mr. Selz, warning me against ‘pawn snatching’; that is grabbing a minor point that can lead to defeat because the position was not thoroughly analyzed. MATE, however, is correct in this analysis and can safely seize the objective.

While, at Antietam, Battle Group #1 (all the cavalry of the Army of the Potomac commanded by Brigadier General Alfred Pleasonton) is frozen ‘in reserve’. This is not a case where MATE can snatch a pawn. MATE looked at the situation and said, ‘nope’, there are no unattended Victory Points to snatch and there is not an open flank to exploit so, the default setting is ‘in reserve’.

This leads to the interesting conundrum: what exactly was the Union cavalry at Antietam doing? Honestly, I had never really thought of it before. Now, when I look into the question I find, Was McClellan’s Cavalry Deployment at Antietam Doctrinally Sound? This monograph argues that McClellan massing his cavalry in the center for a great coup de grâce exploitation of a breakthrough across the Middle Bridge was acceptable within the framework of Jomini’s theories as taught at West Point before the Civil War. But, then it is countered with this:

In Landscape Turned Red, Stephen Sears has this to say: Shortly before noon, McClellan had ventured to push several batteries across the Middle Bridge, supported by Pleasonton’s cavalry and a force of regulars from George Syke’s Fifth Corps. He was nervous about the move-it was taken against the advice of Porter and Sykes-and he cautioned Pleasonton not to risk the batteries unduly. As an afterthought, he asked, “Can you do any good by a cavalry charge?” Pleasonton wisely ignored the suggestion. – Sears, Stephen, Landscape Turned Red: The Battle of Antietam, New York: Ticknor and Fields, 1983. page 271. (as cited in above)

Would a great massed cavalry attack across Middle Bridge have been suicide? Or brilliant? For the first time in memory I took the 1st edition of McClellan’s Own Story off the shelf and discovered… nothing. McClellan died suddenly of heart failure just as he was writing about Antietam and his memoirs end abruptly with very little insight into his side of the story. But, using cavalry to support horse artillery – rather than the other way around – seemed a bit odd.

I do not know of any other great cavalry charge in the American Civil War than Sheridan at Five Forks (above). Is this what McClellan envisioned at Antietam? Would it have worked? Could American Civil War regiments have formed square against a massed cavalry charge?

Moving on, let’s drill down to the Course of Action (COA) for Blue Battle Group #3 (Burnside’s IX Corps) at Antietam:

MATE tactical analysis for Blue Battle Group #3 at Antietam (Burnside’s IX Corps). Screen shot. Click to enlarge.

The author walking across Burnside’s Bridge in 1966 (age 12).

The above is MATE’s output that concludes with the COA for Burnside’s IX Corps. Perhaps, the greatest mystery of the battle of Antietam is what took Burnside so long to take this bridge (now forever linked with his name)? It is true that there were numerous, futile and bloody attempts to cross it. Note that MATE, above, recognizes the bridge as a critical Choke Point. When MATE sees a Choke Point that is within the enemy’s control (see statement #8, above, “Chokepoint (bridge) is under Red’s Range of Influence ROI = 5958″ and 5,998 is very high ROI value) it brings up artillery (see statements #9, #10, #11, #12, above). All the artillery in the IX Corps is to be within 630 meters of the objective. Why 630 meters? Because at that distance it is guaranteed a 50% accuracy rate. This rate, by the way, was set in the Army Editor:

The accuracy curve for the 1st Division, IX Corps artillery as set in the Army Editor. Screen capture. Click to enlarge.

So, MATE says ⁵⁾I apologize but I find it easier to describe how the AI works using such phrases as ‘thinks’, ‘says’, and ‘decides’. It’s not worth straining over. Trust me, “My objective is a Choke Point. I’m not sending my units into a meat grinder. I’m sending artillery to a point where they are guaranteed a 50% accuracy per volley and have a clear 3D Line of Sight to the target. This is how I’m going to project as much force as I can at the objective.” War is about force projection. MATE knows this. Is this a better plan than what Burnside actually did? Yeah, it is a lot better with a far greater probability of success. I’ve stood on that plain just east of Burnside’s Bridge and thought that nine batteries of 12 lb. Napoleons aimed at the crest of that hill just beyond the bridge would provide a substantial amount of force projection and covering fire. About half an hour of force projection followed up with an infantry assault would probably take the bridge.

I once described good AI as: Don’t do anything stupid, fast. MATE is doing that. I think MATE is on the way to beat most human opponents because humans do stupid things, fast.

We’ll see. Should be an interesting journey.

References[+]

References
↑1	MATE: Machine Analysis of Tactical Environments
↑2	see http://riverviewai.com/download/SidranThesis.pdf
↑3	a flank that is attached to or protected by terrain, a body of water, or defended fortifications.
↑4	see pages 45-6 http://riverviewai.com/download/SidranThesis.pdf
↑5	I apologize but I find it easier to describe how the AI works using such phrases as ‘thinks’, ‘says’, and ‘decides’. It’s not worth straining over. Trust me

A Human-Level Tactical Artificial Intelligence at Ligny

6 Replies

Map 159 from the superb, “West Point Atlas of the Napoleonic Wars,” (Esposito & Elting, 1999, Stackpole). Scanned from the author’s collection. Click to enlarge.

The seeds of Napoleon’s defeat at Waterloo were sown two days earlier at his victory near Ligny. Napoleon needed to surround and completely remove the Prussian army as a viable force on the battlefield. Instead, they escaped to Wavre in the north and resurfaced at the worst possible time on Napoleon’s right flank two days later at Waterloo.

MATE¹⁾Machine Analysis of Tactical Environments 2.0 is now capable of analyzing the battle of Ligny, June 16, 1815 from both the Blue (L’Armée du Nord on the offensive) and Red (Prussian on the defensive) positions. (MATE is the AI behind General Staff: Black Powder. For more information about MATE see these links).

The Ligny map was donated by Glenn Frank Drover. Jared Blando is the artist. Ed Kuhrt did the elevation, roads and mud terrain overlays. The unit positions are from the West Point Atlas of the Napoleonic Wars (above) and from David Chandler’s Waterloo: The Hundred Days. If any one has a better source for unit positions, please contact me directly.

Screen capture of the Ligny scenario in General Staff. Elevation and slope layers enhanced.

Below is MATE’s analysis from the Blue (L’Armée du Nord) perspective. MATE correctly identifies the key positions and realities of the battlefield:

Red is on the defensive
Red has an exposed flank
There are two key choke points on the route to Red’s exposed flank

MATE then creates an appropriate Course of Action (COA) for Blue:

Battle Group #1 (The French III Corps) is assigned the flanking maneuver.
Battle Group #0 (The Imperial Guard) is assigned the objective of St. Amand with the support of Battle Group #4 (IV Corps cavalry and reserve artillery).
Battle Group #2 (IV Corps) demonstrates against Ligny.
Battle Group #3 (The Cavalry Reserve) seizes Balatre and a crucial bridge located there.

MATE’s analysis of Blue’s position at Ligny. Screen capture. Click to enlarge.

A log of MATE’s thought processes, with my commentary, follows:

Text output of MATE’s analysis of Blue’s position at Ligny. Click to enlarge.

MATE also analyzed Ligny from the Prussian (Red) perspective:

Screen capture of MATE’s analysis of Ligny for Red (Prussian army). MATE recognizes the two choke points on the route of the enemy’s flank attack and dispatches cavalry units to cover these critical areas. Click to enlarge.

MATE, analyzing the Prussian (Red) position correctly recognizes that it is on the defensive, it has an exposed flank, there are two crucial choke points on the route that Blue will take on its flanking maneuver and dispatches two cavalry units to cover the bridges. A log of MATE’s thought processes, with my commentary, follows:

Text output of MATE’s analysis of Red’s position at Ligny. Click to enlarge.

Critique of MATE’s analysis:

As the author of MATE any critique I have of its performance should be taken with a grain of salt (also, see this video). If I was back in academia I would put together twenty or thirty Subject Matter Experts (SMEs), set up a double blind web site, get all the SME’s solutions to the problem, and compare their solutions to MATE’s. If they match to a statistical significance it proves the ‘human-level’ part. But, I’m not in academia anymore and you’ll just have to take my word for it. That said, MATE did what I expected it to do.

It first sussed out if it was on offense or defense and what it had to do to win.

Then, as Blue, MATE discovered a back door to Red’s position and ordered a classic enveloping maneuver. MATE assigned Blue Battle Group #1 the task of implementing the flanking maneuver. Blue Battle Groups #0, #4 and #2 are the fixing force. See my paper, Implementing the Five Canonical Offensive Maneuvers in a CGF Environment (free download here) for details and algorithms. The Blue Cavalry Reserve is given the COA to seize the town of Balatre. This, in my opinion, is a pretty good tactical plan.

When MATE finds itself on defense, as it does as Red at Ligny, one of the first things it does is ask itself, “how would I attack myself?” So, of course it finds the back door right away. Then it compiles a list of available units that are not actively engaged in holding crucial parts of a defensive line, selects the optimal (fastest) units and assigns them orders to defend the crucial choke points. This was a better plan than Field Marshal Gebhard Leberecht von Blücher had. So, again, I’m going to argue that MATE is operating at a ‘human-level’.

As always, please feel free to write me with the questions or comments. MATE is going to take a look at Antietam next.

References[+]

References
↑1	Machine Analysis of Tactical Environments

A Human-Level Tactical Artificial Intelligence at Bull Run

References
↑1	Machine Analysis of Tactical Environments 2.0
↑2	1995, Stackpole Books, Mechanicsburg, PA
↑3	to understand profoundly and intuitively from Heinlein’s Stranger in a Strange Land

Why Machines May Kill Us In Our Sleep

4 Replies

An amazing screen capture of the AI’s solution to a problem. It has found a 1 pixel gap between the data and the edge of the screen and is exploiting it to successfully find an ‘open flank’ of Red. Click to enlarge.

Professor Alberto M. Segre was my thesis advisor and one day he said to me, “You know when your AI is really working because it will surprise you.” Today I got to have one of those weird surprises.

The screen shot (above) is a visual representation of what the AI is up to. You won’t get to see this in the actual game. The program that’s running is called the AI Editor which is a bit of a misnomer because you don’t actually edit the AI in it; you mostly just get to observe what it’s doing. There’s a lot of stuff going on in the above image. There are multiple layers visually displaying different types of data (check out the blog – Layers: Why a Military Simulation is Like a Parfait – for more information about these). But, what interests us are the AI layers: Battle Groups, Objectives, and that thin yellow line that snakes from a group of blue units, crossing Antietam Creek at the Middle Bridge and then, amazingly, exploiting a data anomaly to reach its goal: a point far behind enemy lines.

Some background on the situation:

The map of the Antietam Battlefield (screen shot) with terrain and elevation layers displayed. Click to enlarge.

Underlying all the clutter from the first screen capture, top, is the battle of Antietam (above). The map has been rotated 90 degrees to the left so north is now pointing to the left; east is at the top of the screen.

After adding Blue (Union) and Red (Confederate) units to the map in their historical positions at 0600 September 17, 1862 the AI performed a tactical analysis from the perspective of Blue.

The AI ‘strategic’ analysis for Antietam playing Blue (Union).

The above are a list of Predicate Statements all of which the AI knows to be true. Statements preceded by the logical sign ∴ (therefore) are conclusions, or inferences, derived from the predicate statement referenced in the brackets. It is this analysis that determines if the AI will be on the offensive or defensive and what its objectives will be.

Next, the AI performs Range of Influence (ROI) calculations for the entire observable battlefield. I plan on doing a video about this later, but for now the darker the red (in the topmost screen capture) the more – and more powerful – weapons the Red army can bear on that point. The AI next divides all the units on the map into a forest of minimum spanning trees called Battle Groups. I want to do a video about this, too. However, if you can’t wait, these subjects are covered in my paper, Implementing the Five Canonical Offensive Maneuvers in a CGF Environment (free download).

Again, referring to the top screenshot you can see the AI’s calculations to this point:

It has determined it (Blue) will be on the offensive.
It has calculated enemy ROI.
It has assigned objectives to the first Battle Group.

Flanking Algorithm published in, “Algorithms for Generating Attribute Values for the Classification of Tactical Situations”. Click to enlarge.

Now the AI needs to determine if the enemy has an ‘open or unanchored flank’. In Algorithms for Generating Attribute Values for the Classification of Tactical Situations I published the Algorithm for Flanking Attribute Value Function (right). It basically comes down to this: can the AI trace an unbroken path from the center of the Blue Battle Group to a specific point (called the Retreat Point) far behind enemy lines without crossing into ‘No Go Areas’ (water, swamp) or entering any area controlled by Red’s ROI (literally the red areas in the topmost screen shot).

The reason that I was using Antietam as a test case for anchored / unanchored flanks is because years ago I had analyzed the battle for my doctoral thesis and knew it to be a classic example of anchored flanks; Lee’s left flank rests on the Potomac and his right flank is anchored on the Antietam. Granted, the Confederate flanks were held by Stuart’s cavalry with a little horse artillery support but they were still, by definition, anchored flanks.

Due to an error in the data that made up the Antietam terrain map a 1 pixel (about 3.8 meter wide) strip of ‘no terrain’ was inserted at the far right hand edge of the map (see blow up of screen capture, right; it’s the thin line between the water, represented in red, and the brown edge of the map). This meant there was a ‘land bridge’ across Antietam Creek where none existed in real life. A digital parting of the Red Sea, if you will. But, by the rules of the game the AI perfectly performed its function. There was no error in the AI – again, the AI performed better than I had dared hope – the error was with the data set.

And that’s how fifty years from now I can see a cyber-detective standing over the chalk marks around a body saying, “Yeah, the machine performed perfectly, brilliantly, in fact. But, the error in the data set killed him.”

It’s already happened in real life. For cars with autopilot the data set of the world in which it operates is crucial. However, “against a bright spring sky, the car’s sensors system failed to distinguish a large white 18-wheel truck and trailer crossing the highway, Tesla said. The car attempted to drive full speed under the trailer, “with the bottom of the trailer impacting the windshield of the Model S”, Tesla said.” The driver died. The AI functioned perfectly. But, the error in the data set killed him.

So, I fixed the error in the data set (probably caused by not using the right values in InkScape when I converted the Antietam Water.bmp into paths) and imported it back into the Antietam map using the General Staff Map Editor, saved it out, and ran the AI Editor again and saw this:

The AI did not display a yellow path from the center of the Blue Battle Group to the Red Retreat Point because none existed. Instead, it just wrote the first Predicate Statement in the Tactical Analysis stack: “Red’s flanks are anchored”.

Again, the machine was performing perfectly. And its results were no longer surprising.

Addendum

I recently got to experience this again (though this time it was caused by a different data bug) when I was reviewing the AI’s decisions at the battle of Manassas:

Because the Range of Influence was not calculating the very bottom row the AI found another, perfectly legal, way to reach its goal. Screen shot from the General Staff AI Editor. Click to enlarge.

In this instance, the error in the database was caused by the Range of Influence (basically a map of what red and blue can see and hit) not calculating the very last row. Consequently, the AI was able to legally trace a path from the blue forces in the northeast to their goal at the bottom of the map.

After this bug was corrected the AI performed as expected:

The AI correctly sees going around red’s left flank as the solution to the problem. Screen shot from General Staff AI Engine. Click to enlarge

In the above screen shot the AI has demonstrated the correct solution to the tactical problem facing blue at Manassas on July 20, 1861 (the day before the actual battle). Red’s left flank is unanchored. It’s wide open. Note how the AI identifies the one choke point (Sudley Springs Ford) in the plan.

So, the AI surprised me again. I think it’s looking pretty good. When you play against it, watch your flanks.

Ty Bomba’s Primer on Strategy & Tactics