Almost two years ago, I posted the following observations on BOA2 AI played under Official 1.05:
http://www.ageod-forum.com/showthread.php?t=15345&page=2
Unfortunately, the campaign is still not much of challenge - after the first 12-15 months I routinely manage to dominate the game, which becomes a military procession to victory interrupted by bouts of Yankee whack-a-mole. The main problems seem to be as follows.
Failure to Regroup: Athena will reliably concentrate a good-sized force under Washington, but if (when) this main army is defeated she doesn't seem to know how to regroup. I rarely see another large army after defeating the first, even years later after plenty of time to rebuild and reconcentrate troops. Instead, from that point on Athena will rely on a scattering of smallish forces in various theatres.
Misuse of leaders: Often related to the above point, after the initial engagements Athena doesn't seem programmed to do what a human would do, pull back the remnants or at least the commanders to form a new main force. Instead, Washington will continue to command an ever-shrinking army in a single region, sometimes past the point of absurdity. In my most recent game, he was defeated in Maryland in mid-1776 and driven into the Virginian Appalachians to watch the remnants of his army starve through the winter, spent most of the next campaign leading a handful of units in the same vicinity until tracked down and destroyed utterly, and then suddenly reemerged some time afterward leading an Indian war-party in a raid on Presque-Ile (of all things!). The obvious course would have been to withdraw him and whatever was left of the Continental Army to the Hudson Valley or New England and draw together another field army. Lesser leaders like Gates or Howe behave the same way - once their initial field force is beaten, they hang around leading a few regiments of militia in futile raids on British garrisons.
Dispersal of effort: Granted, AI is never good at long-range planning, but not uncommonly resources which might have been capable of prying a strategic town or two free if they had been concentrated on a single region instead get used in penny-packets - the result in the mid-game is whack-a-mole, with little groups of rebels popping up, only to be run down by my ranger-indian-dragoon columns.
What can be done about these related problems? Is there a parameter for force concentration which applies across the board and which can be adjusted slightly - not too much, since some small-scale raiding is valuable in tying down British garrisons? Is it possible to beef up a "self-preservation" AI routine which would direct the AI logic to pull out of an area and run for cover when nearby enemy forces are overwhelming? Or perhaps a single recurring event can direct Washington to the largest Yankee stack if his own falls below a certain strength, which would at least keep him from wasting his talents leading Indian raids?
Over the last few days I've reinstalled BOA2 and tried the same campaign, 1775-83, so it might be of interest to compare my experiences then and now.
First, it is still not much of a challenge - after taking New York as soon as Howe's army arrived, in early 1776, I was pleased to see that the AI had responded by concentrating a sizable army roughly equal to my own under Washington in Westchester and counter-attacking to re-take New York. Had Washington succeeded, it might have meant game victory for the AI. But he didn't.
Afterwards, Washington retired up the Hudson and I lost track of the Continental Army for a time. Meanwhile, I proceeded with a methodical conquest of New England, taking everything but Norwich by year's end, and encountering only small or middling forces which were handily defeated. Washington reappeared in early autumn before the gates of Ticonderoga (which I had retaken by a rapid coup de main from the Vermonters). With a depot and around 200pts of troops under Carleton, an assault wasn't likely - so after a few months' siege, Washington withdrew when the snow began to fall.
I can't say how the CA was supplied during this abortive siege - it would be interesting to know if the AI is up to the job of keeping a regular supply line in operation, rotating supply units from the force to a supply source like Albany. If not, Washington must have suffered some serious attrition in such a remote place.
However, the campaign of '77 opened with the CA cut off from the rest of the colonies in the Hudson Valley, and two British armies poised for an offensive: Howe's at New York and a promoted Grey based on Springfield. Despite Howe completely muffing it and never arriving, Grey was able to advance on Albany, defeat Washington there, and seize the depot.
The Continental Army was forced to retreat up the Mohawk to Ft. Stanwix, where attrition began to bite hard, but even so the third great battle of the war was by no means a forgone conclusion. The rest, however, was. With the last clear month of the war, Grey arrived before Ft. Oswego and took it by storm, bagging the remnants of the Continental Army and presumably Washington himself (at least, I've seen no trace of him since). Everything since has been mop-up operations - in effect, the American rebellion is over.
So how does this compare to my experience under 1.05?
In the first place, Washington did regroup from his first defeat at New York, sufficiently to be able to offer two further large battles at Albany and Ft. Stanwix. While there are (were) subsidiary forces operating elsewhere, the penny-packet dispersal I noted above seems much less pronounced and more sensible. Moreover, the AI seems to have learned to reinforce the Continental Army - even after Albany, when I expected a lean enemy at Ft. Stanwix, the AI seems to have reinforced Washington somehow.
The misuse of leaders issue is harder to judge. Certainly, at Albany or certainly after Ft. Stanwix, when it was clear that the CA was caught in a deathtrap in the Mohawk Valley, I would probably have detached Washington and had him run for PA or VA to rebuild a main field force. On the other hand, it's possible that the CA, reduced as it was, may still have been the largest field force available, in which case perhaps the AI was simply following a sensible protocol to keep Washington with the largest force.
On the third hand, in other regions I have yet to see an important secondary commander (e.g. Gates) wasted by leading a band of Indian raiders or a single militia battalion, which would have been common under 1.05 (Washington at Presque-Isle!), so perhaps that's a good sign.
So, in conclusion, it seems the AI has significantly improved its regrouping and dispersal problems. Leader misuse has to be given a verdict of "unproven". The overall strategic logic of the AI is still questionable - moving up the Hudson to Ticonderoga was a gutsy move which would have appeared brilliant if the fort had fallen, but instead proved a fatal error. But at least it was a move with an obvious logic. It may be that the geographic realities of BOA2 - a long, thin region to defend rather than a compact territory with obvious interior lines such as the Confederacy or Prussia - will always make it difficult for any AI.
I think there are many more helper AI events in WIA then ROP. They are in the events folder in WIA.