Forged Alliance Forever

Re: So, I made an AI for FA

2016-05-29T20:31:19+02:00

These are 'squad' designations. By themselves, they have no particular meaning. They simply allow you to give unique orders to groups of units inside a platoon. For example, you could give a move order to the Attack units, an attack move order to the Artillery squad and an assist order to the Guard units.

When the platoon, as a whole is given an order, the squad designations don't do anything, the platoon will form as you would expect of the whole group, but you can give individual movement orders to the squads, with different formations. Here is a sample command;

IssueFormAggressiveMove( platoon:GetSquadUnits('Artillery'), waypointPath, 'AttackFormation', 0)

Hope this helps answer your question

Statistics: Posted by Sprouto — 29 May 2016, 20:31

Re: So, I made an AI for FA

2016-05-29T08:15:01+02:00

https://github.com/HardlySoftly/Forged- ... es.lua#L14

First question mark is one of these:

'Attack'
'Support'
'Artillery'
'Scout'
'Guard'
'Unassigned'

What it does? That's a good question So far what I've seen was if I made a platoon with multiple units, and they were in formation(second question mark) unit's that were marked as 'attack' moved in one group, those with 'guard' in second. So that split the platoon into two groups. Problem I had with that was that 'guard' units were usually faster (cruisers, subs, shiels) so they were always in front of 'attack' (destroyers, frigates, tanks).

It should be handeled here? https://github.com/FAForever/fa/blob/develop/lua/aibrain.lua#L2655 So if you feel like investigation what it does and explaining it I'd be happy.

Second question mark is formation. There are currently 3 formations used in FA:

'AttackFormation' - Wide formation
'GrowthFormation' - Compact one
'None' or 'NoFormation' - self explaining

Vannila supcom had more formations. From those I remember: 'ChevronFormation', 'TravellingFormation'. There are all the fancy formations. They do work in FA as well, so if you really want them, feel free to do so, but I agree with GPG here and things that Attack and Growth are more than enough ^^

Statistics: Posted by speed2 — 29 May 2016, 08:15

Re: So, I made an AI for FA

2016-05-28T01:28:58+02:00

I've updated the code again to make the AI better, it can now consistently beat the Sorian AI on desert arena. This has been done while keeping the code really short and simple so people can pick up on it and understand it easily.

Next stop is to add some more sophisticated features, I'm planning on seeing how good I can get it at the desert arena map.

Statistics: Posted by Softly — 28 May 2016, 01:28

Re: So, I made an AI for FA

2016-05-27T22:16:34+02:00

Perhaps the most important thing for the AI is intelligence gathering.

All of it's decisions are based upon it's current assessment of threat. It has a VERY short memory, so very frequent intelligence gathering is an absolute must for the AI. Simply pushing units out onto the map is the reason why the K/D ratio of the AI is so incredibly poor. Without accurate and up-to-date threat values, the AI cannot make good choices about which targets to attack, and which to avoid, with any given platoon of units.

Understanding how the AI collects intelligence information, and how it uses it (ie. - the existing Threat Map) will allow you to bring a higher level of smarts to the AI.

For those that might be unaware, the Threat Map is simply a checkerboard (16 by 16 tiles) that is applied to EVERY map. As the AI sees units in each of those tiles, the threat value for that tile is adjusted. When the AI cannot see a tile, the threat level fades out fairly quickly (between 30-60 seconds). Most of the AI routines (both stock and Sorian) use this map to determine not only targets, but select movement paths, so you can see how vitally important it is.

Statistics: Posted by Sprouto — 27 May 2016, 22:16

Re: So, I made an AI for FA

2016-05-27T04:08:47+02:00

More realistic suggestion: Teach the AI how to make and effectively use ghetto gunships. This is something that I would think would be a small challenge seeing as it wouldn't be "intuitive" for an AI.

Second Realistic Suggestion(Even "easier" one imo): Teach the AI how to use engies and engineering stations to assist factory production.

Also, I have put some thought into things the FA AI is already good at. Kind of a pros/cons list.

Things AI is good at:
AI is good at expanding; managing many bases at once; taking and controlling the map

Things AI is not so good at:
Micro in any form; skillful eco management; hard teching; using engies to assist factories

Play any match against the AI on a 20x20km map and you'll find that it expands a lot faster than you in every direction. It will most likely take early map control and hold it for a little while. That's because the AI is good at being at many places at once. This would require very high apm and concentration from any good player to replicate. Not to say you won't run it over in 10 minutes when you have 3x the eco and big tech advantage, but that's the point of this thread then isn't it?

Statistics: Posted by Astrofoo — 27 May 2016, 04:08

Re: So, I made an AI for FA

2016-05-27T02:12:48+02:00

Anihilnine wrote:
I can and will do 1,2,3 if someone can show me they can do 4 and 5

4 and 5 are the magic bits though!

Statistics: Posted by Softly — 27 May 2016, 02:12

Re: So, I made an AI for FA

2016-05-27T02:08:37+02:00

I can and will do 1,2,3 if someone can show me they can do 4 and 5

Statistics: Posted by nine2 — 27 May 2016, 02:08

Re: So, I made an AI for FA

2016-05-26T22:10:22+02:00

Hopefully some people will try running my AI, or browse the code a bit to see how it works.

Also can I recommend we start with some more realistic suggestions?
e.g. Could you teach this AI to make an air factory? (The answer is yes)

I'm open to contributing to some kind of standard machine learning API for the AI, but if you're going to make suggestions on this front then I'd ask you put some proper thought in first. Giving a list of "1) watch/play games 2) Do magic 3) iterate" won't get us any closer

Statistics: Posted by Softly — 26 May 2016, 22:10

Re: So, I made an AI for FA

2016-05-26T09:48:04+02:00

So a AI that can learn from the player's actions?

Spoiler: show

Statistics: Posted by zeroAPM — 26 May 2016, 09:48

Re: So, I made an AI for FA

2016-05-26T09:11:46+02:00

You can learn the entire replay vault.

1. branch fa lua code, including dump of critical information
2. run the replay with the branched code, dumping out info
3. automate downloading all replays, running them, collating info
4. run machine learning over all that and know how to be awesome
5. construct an AI to use that info and play against real people

1-3 are possible.
4 is interesting.
5 is too ambitious and would never happen.

Statistics: Posted by nine2 — 26 May 2016, 09:11

Re: So, I made an AI for FA

2016-05-26T06:39:04+02:00

When AI will notice players players do certain things, it also need to see what triggers those behaviours, but just from replay it can't know unit position or health (you will have to run simulation) , and AI will need those to have any success, basic ability to retreat in front of a bigger army or kite or reduce unit production if all choke points have defence...

Sounds like you need AI with some advanced UI mods to help it do micro

Machine learning in FA sounds very complex to me.
Afaik machine learning AI with combination of stealing moves from best players, just managed to master GO and that was kinda big advancement.

Statistics: Posted by ZLO_RD — 26 May 2016, 06:39

Re: So, I made an AI for FA

2016-05-26T05:07:13+02:00

Anihilnine wrote:
I think you're being a little sensitive but whatever.

Machine learning is a cool idea.. Just analyze the replay vault.

But that to me sounds way too ambitious...

I'm not being too sensitive, it was just a stupid remark.

Well the concepts of machine learning aren't really ambitious, as it's just techniques built on-top of each other, so it's just a slow iterative process. The only real hindrance would be what's available for the AI to actually see as I stated previously. I don't think we could really analyze a replay file itself, rather we could just throw it up in ladder and have it learn there, providing both a "player" for others to play against and a way to train the AI. If someone wants to go this route I would love to help, I'm aware of a bunch of AI concepts, but not experienced enough to do this on my own.

Statistics: Posted by Aulex — 26 May 2016, 05:07

Re: So, I made an AI for FA

2016-05-26T05:00:14+02:00

I think you're being a little sensitive but whatever.

Machine learning is a cool idea.. Just analyze the replay vault.

But that to me sounds way too ambitious...

Statistics: Posted by nine2 — 26 May 2016, 05:00

Re: So, I made an AI for FA

2016-05-26T04:49:50+02:00

Anihilnine wrote:
Its amusing

It's a waste of space

To follow up on my machine learning remark, something as simple as reinforcement learning could be used, the only question is what is available to the AI brain to help train the model.

Statistics: Posted by Aulex — 26 May 2016, 04:49

Re: So, I made an AI for FA

2016-05-26T04:34:10+02:00

Its amusing

Statistics: Posted by nine2 — 26 May 2016, 04:34