Artificial intelligence in 1v1 diplomacy

Use this forum to discuss Diplomacy strategy.
Forum rules
This forum is limited to topics relating to the game Diplomacy only. Other posts or topics will be relocated to the correct forum category or deleted. Please be respectful and follow our normal site rules at http://www.webdiplomacy.net/rules.php.
Post Reply
Message
Author
General Subutai
Posts: 2
Joined: Wed Jul 04, 2018 12:43 pm
Karma: 4

Artificial intelligence in 1v1 diplomacy

#1 Post by General Subutai » Thu Jul 05, 2018 11:04 pm

I am very curious as to whether an AI can be developed for FvA and GvI variants, where the AI teaches itself how to play diplomacy by playing thousands upon millions of games against itself, in a similar manner to the Dota2 OpenAI, Google's AlphaGo and AlphaZero.

I am a complete layman in the field of machine learning.

One may ask, what's the point of developing a superhuman AI that can play better than any human player? I think it may be a fun (if ultimately exhaustive/depressing) experience to play against it in 1v1. It's likely we'll see some novel early to midgame openings and unexpected tactics/gambits on behalf of the AI. It will provide a challenge to players to find unexpected methods to beat the AI, perhaps using unorthodox strategies. It would also be interesting to watch a highly skilled human play against the AI, and what sort of games the AI plays against itself.
4

Foxcastle
Posts: 1002
Joined: Sat Dec 30, 2017 11:48 pm
Location: Night Vale
Karma: 50

Re: Artificial intelligence in 1v1 diplomacy

#2 Post by Foxcastle » Thu Jul 05, 2018 11:48 pm

Look, if you want Xorxes to give you some pointers, you probably just have to ask...
1

General Subutai
Posts: 2
Joined: Wed Jul 04, 2018 12:43 pm
Karma: 4

Re: Artificial intelligence in 1v1 diplomacy

#3 Post by General Subutai » Fri Jul 06, 2018 3:04 am

I think it's conceivable for a modern machine learning program to train itself not only to reliably defeat very skilled players like Xorxes, but also to do so in an incredibly short time period

With just 4 hours of training time (and 44 million games of playing against itself) AlphaZero defeated the sophisticated chess engine Stockfish

CptMike
Posts: 189
Joined: Sun Dec 31, 2017 8:12 am
Location: Liège, BE
Karma: 17

Re: Artificial intelligence in 1v1 diplomacy

#4 Post by CptMike » Fri Jul 06, 2018 7:09 am

General Subutai wrote:
Fri Jul 06, 2018 3:04 am
I think it's conceivable for a modern machine learning program to train itself not only to reliably defeat very skilled players like Xorxes, but also to do so in an incredibly short time period.

With just 4 hours of training time (and 44 million games of playing against itself) AlphaZero defeated the sophisticated chess engine Stockfish
That's very interesting and worth developing, even more if the IA can learn in simulating games. I am confident that IA will very fast reach a very good level, if not the first rank, but human will come back and win at the end, learning the way the IA plays.

GvI and FvA are at the same time easier and more complex than go. The new element if the fact that movements are simultaneous and odds take a relevant part in the game even if there are no dice.

Very impressed that AlphaGo leart in 4 hours how to beat a chess programm... That seems to prove that machine learning learns strategies and does not calculate all the possibilities !

y2kjbk
Posts: 1091
Joined: Thu Oct 19, 2017 4:23 pm
Karma: 15

Re: Artificial intelligence in 1v1 diplomacy

#5 Post by y2kjbk » Sat Jul 07, 2018 9:39 am

It would be feasible to do but not as straightforward as a chess program since you’re dealing with incomplete information concerning the exact state change that your move will have on the game, even if the range of necessary board states to consider is smaller. You’d have to incorporate aspects of programs they’ve made that can play poker.

CCR
Posts: 39
Joined: Sun Dec 31, 2017 4:51 pm
Karma: 1

Re: Artificial intelligence in 1v1 diplomacy

#6 Post by CCR » Sat Jul 07, 2018 12:08 pm

It already exists, in theory.
The wonderful Albert bots can play in any map available on the Daide mapper engine.
1

CptMike
Posts: 189
Joined: Sun Dec 31, 2017 8:12 am
Location: Liège, BE
Karma: 17

Re: Artificial intelligence in 1v1 diplomacy

#7 Post by CptMike » Sun Jul 08, 2018 7:40 pm

CCR wrote:
Sat Jul 07, 2018 12:08 pm
It already exists, in theory.
The wonderful Albert bots can play in any map available on the Daide mapper engine.
Albert is not very strong...

CCR
Posts: 39
Joined: Sun Dec 31, 2017 4:51 pm
Karma: 1

Re: Artificial intelligence in 1v1 diplomacy

#8 Post by CCR » Sun Jul 08, 2018 11:14 pm

I challenge you - all of you - to play 7 games agaisnt 6 of the latest alberts.

Then post here your results.

References:
Albert bot:
https://sites.google.com/site/diplomacyai/home/daide
DAIDE server and mapper:
http://www.ellought.demon.co.uk/dipai/

bozotheclown
Posts: 810
Joined: Sun Dec 31, 2017 8:13 am
Karma: 2

Re: Artificial intelligence in 1v1 diplomacy

#9 Post by bozotheclown » Mon Jul 09, 2018 5:21 am

CCR wrote:
Sun Jul 08, 2018 11:14 pm
I challenge you - all of you - to play 7 games agaisnt 6 of the latest alberts.

Then post here your results.

References:
Albert bot:
https://sites.google.com/site/diplomacyai/home/daide
DAIDE server and mapper:
http://www.ellought.demon.co.uk/dipai/
Has this AI ever been tested in 1 vs. 1?

ghug
Admin
Admin
Posts: 1198
Joined: Mon Mar 20, 2017 3:51 pm
Location: Seattle
Karma: 372

Re: Artificial intelligence in 1v1 diplomacy

#10 Post by ghug » Tue Jul 10, 2018 11:34 pm

Is important to remember that Google has gigantic pieces of specialized hardest to put behind AlphaGo. That 4 hour number isn't really meaningful unless someone here wants to shell out a big chunk of change for TPU time.

I don't think a 1v1 AI would need to be nearly as sophisticated though. People correctly note the added complexity of concurrent movement, but both of our variants are very limited in the amount of "reasonable" movesets at any given time, to the point where I think reinforcement learning techniques could very quickly iterate to a point of competence from which to expand.

CptMike
Posts: 189
Joined: Sun Dec 31, 2017 8:12 am
Location: Liège, BE
Karma: 17

Re: Artificial intelligence in 1v1 diplomacy

#11 Post by CptMike » Wed Jul 11, 2018 12:42 am

ghug wrote:
Tue Jul 10, 2018 11:34 pm
[...] reinforcement learning techniques could very quickly iterate to a point of competence from which to expand.
Let's try it...

rdrivera2005
Posts: 911
Joined: Tue Oct 31, 2017 5:17 pm
Location: Porto Alegre, Brasil
Karma: 31

Re: Artificial intelligence in 1v1 diplomacy

#12 Post by rdrivera2005 » Wed Jul 11, 2018 4:28 am

Do you really think Xorxes isn't a bot?
1

Yigg
Posts: 28
Joined: Sun Dec 31, 2017 3:56 am
Location: Wisconsin, United States
Karma: 17

Re: Artificial intelligence in 1v1 diplomacy

#13 Post by Yigg » Wed Jul 11, 2018 5:12 am

You know, I've already seen this movie. I don't like how it ends.

xorxes
Posts: 598
Joined: Sun Dec 31, 2017 9:45 am
Karma: 96

Re: Artificial intelligence in 1v1 diplomacy

#14 Post by xorxes » Fri Jul 13, 2018 11:19 pm

Daisy, Daisy,
Give me your answer do...
I'm half crazy,
All for the love of you...

David E. Cohen
Posts: 36
Joined: Thu Jan 25, 2018 1:27 am
Karma: 7
Contact:

Re: Artificial intelligence in 1v1 diplomacy

#15 Post by David E. Cohen » Sun Aug 12, 2018 7:04 am

Look Dave, I can see you're really upset about this. I honestly think you ought to sit down calmly, take a stress pill, and think things over.

Post Reply

Who is online

Users browsing this forum: No registered users and 2 guests