Improved Pro AI, please give it a try and post feedback
-
@Schulz would you mind attaching a save game for the scramble case. I'll try to look into the others.
-
-
@LaFayette It has actually more to do with the fact that the Russians TUV is the most valuable. Since Russians are the primary Axis target and are semi-isolated from the rest of the Allies, there is the dynamic by which the same Russians TUV is worth more than the same Germans TUV, which in turn is worth more than the same British TUV, which in turn is worth more than the same Americans TUV.
For example (I'm not saying that these numbers are correct.), the AI would need to understand that the Germans TUV is worth 90% the Russians TUV so giving a value to any TUV swing between Germans and Russians valuing the Germans TUV at 90% the Russians TUV, so Russians would end up on par as a matter of TUV if they destroy 10 Germans TUV for every 9 Russians TUV which they lose (destroying the same amount being a bad result for Russians).
I don't know if the AI can maybe be made to understand in general term who is the besieger and who is the besieged at the moment (the besieger being Germans and the besieged Russians at least early on) and so try to be TUV conservative with Russians and try to induce more reciprocal TUV destruction with Germans.
The other element is that in TUV destruction over multiple rounds via territory trading the one with the most air units is advantaged, and again here there is a major superiority of the Germans at least for some rounds (the Germans having many more fighters than the Russians, though of course the Germans fighters are distracted by the other allies much more than the Russians fighters are by Japanese).
For context, I've chosen "World War II v5 1942 SE TR" not because it's a map I know: I've actually never played this map against a human opponent. The reason is that this is the only extremely well balanced map which TripleA has amongst the basic ones. (Notice that this applies to this game but not to the original "World War II v5 1942 Second Edition", which is unbalanced in favour of Axis.)
-
@Cernel I think I have a patch that might be ready in a week that captures this. Essentially the concept of a "Front" as pairing any two clusters of factories. That defines attack paths along which attacking/defending is computed based on how many turns to overwhelm along that path. If there is no chance to overwhelm, then it's a defensive front vs offensive. From there, the income ratios comes into play. Your rule is a bit simpler, but does not generalize very well. If we can determine how to calculate those ratios, we would have a more generic way to establish that.
-
Do you wanna add a ping to the Lobby Intro ? New AI to try post results here type thing ?
Idk
I imagine most Lobby Players blow right by the intro but but even one hit would provide data
I might ping something at the other site too. Seems Revised would be the main game or SE I guess. Idk as I don't play them.
I'm guessining it still doesn't do Politics so Anniversary and G 40 probably won't work but the Objectives definitely a good step.
Hmm ... Maybe Anniversary doesn't have politics ...
just GlobalWell at any rate I might post something under the triplea thread over there.
Maybe @panther has a suggestion for promoting it ?
Good Work Lafayette
-
@LaFayette OK.
As an example of Russians being (obviously, as in every V-series game) the main focus of Axis attention, I've played the game going almost full on Russia and took Moscow round 5 against Hard Beta AI as of version 2026-11.16.15866. (I actually reloaded the game twice in favour of Russians until they had a good round 1 open, but they always played it perfectly: the first two times they just got bad dice.
)
2026-11-2-World-War-II-v5-1942-SE-TR.tsvgIf you take a look at it, is there anything particular I should focus on commenting, or is it all fairly obvious to you by looking through history?
-
@Cernel I'd like you to comment. You have a better feel of what was significant. Second, it's a big time saver. Your comment and save game feeds an AI (Claude) analysis that can patch code, replay the save game, create data sets that the (TripleA) AI can be scored on.
I'm setting it up so that the AI is tested on a variety of different game scenarios. Blunders that it makes, rules it does not understand, and then (TripleA) AI improvements are tested through this battery as well as scored on overall ability.
A really thorough description/summary of the game and key insights is very useful here. If we can get 20 or so of them, that'd be huge. Going through the exercise personally, the playtime took me about 3 hours the write up maybe 10 minutes. Plus, I only know a couple maps deeply, which limits me further.
Processing of feedback is highly automated right now, it's pretty bad ass. I was able to parse out every complaint of the AI, and that was a big source of fixes/improvements.
-
I tried the new AI. It seems a bit more creative in its play and handles naval matters better.
-
Well I posted at the other site lol
https://www.axisandallies.org/forums/topic/42759/major-ai-computer-player-update-to-triplea
-
@beelee Thanks! One nitpick, the latest is also (always) available at the main website: https://triplea-game.org/download/
-
-
@schulz the ProAI didn't have any rules for 'Scramble To Any Amphibious
Assault'Working on a fix for ProAI to know about that, so it would then see the scramble option.
-
@LaFayette I also had this propterty, not sure how it impacted the game.
<attachment name="conditionAttachmentAICompatibility" attachTo="Germany" javaClass="games.strategy.triplea.attachments.RulesAttachment" type="player"> <option name="gameProperty" value="AI Compatibility"/> </attachment>In another game, the hard German AI neither used its ships to sink the British ships more effectively nor defended France properly.
-
Played a game of Classic against the new AI. I was the Axis and the AI played the Allies. It didn't really put up a fight. It kept building bombers and tanks as the British. They eventually had 5 tanks in London for no good reason. The Western Allies invaded Africa early which is good, but they didn't start landing in Europe. It kept massing its fleet for a large invasion but that invasion never came because I defended the coastline properly. In this game, it is key to reinforce Russia as much as possible and the AI didn't do that. It just kept bombing me and let me kill Russia. Honestly I was not impressed by the Allied play, they were making strange and passive moves that made an Axis win inevitable.
The game was won at the end of round 7 because of an Axis economic victory.
-
@VictoryFirst I tried the Hard Beta with the Axis against the Hard with the Allies using Oztea 41, a fairly balanced scenario using the Global Map (and no annoying politics rules).
On turn 9, Berlin fell to a can opener attack where the Americans took Denmark and the British took a barely defended Berlin. Another problem was the Japanese overbuilding air and not having enough ground forces to defeat China.
These were issues the Hard AI also had.
-
Working through all of the latest. I presume everyone is playing against the "Hard(Beta) AI". Please prefer Hard(Beta) AI.
FYI, reminder: Bug fixes, like patches to know about rules, are always updated in both "Hard AI" and "Hard(Beta) AI" both. The "beta" AI uses additional considerations & mechanics and is enabled or disabled with the "beta features" engine setting.
@schulz a patch to make the ProAI (Hard AI)aware of amphibious scramble should be live now.
@rogercooper can-opener happened because (LLM wrote):"The traces found the cause of the Berlin loss, and it is exactly Roger's "can opener": the AI treats the Danish Straits as closed to the British, so it sees no sea-landing threat on Berlin." That can be patched!
Issues found
- It's looking like the excessive bombers is the ProAI deciding to spend excess income on air.
- ProAI is not considering a canal based can opener. It sees a canal as closed, and treats it that way until next round. The ProAI then unstacks because it only see a few units that can attack, so G becomes too lightly defended.
Additional Approach for improvements
I'm realizing a number of issues is the ProAi not being aware of some rules. I'm working to compare a full set of rules with what ProAI knows about to give clues to which rules it should implement. Rockets, paratroopers look to be big ones for that gap.
Hoping to have a number more patches/fixes landed tomorrow night and the day after.
-
Havent tried it will check it out later on middle earth.
To note one thing the Hard Ai has a problem with dealing is capital bait&recapture. It doesnt seem to understand that it must defend the capital when it recaptures lest the opponent take it over again and steal all PUs, could be worth scripting for those outliers.
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better 💗
Register Login