Upcoming Products and AI Project Updates in Master Duel

I, for one, greet our new A.I. overlords with open arms.

-New Structure Deck: Blue-Eyes Max
“A Deck that utilizes a resilient “Blue-Eyes” monster as a trump card. Many “Blue-Eyes” support cards like “The White Stone of Ancients” and “Blue-Eyes Jet Dragon” have effects associated with your Graveyard. Ensure to monitor the status of your Graveyard closely. Preparations complete and powerful monsters like “Blue-Eyes Chaos MAX Dragon” called upon, imminent and complete victory is just around the corner!

Included cards:
Blue-Eyes White Dragon (UR)
Blue-Eyes Alternative White Dragon (UR)
Blue-Eyes Chaos MAX Dragon (UR)

Available on February 7th (time zones applying)

-New Selection Pack: Ride into the Future
Included cards:
Diabellstar the Black Witch (UR)
Snake-Eyes Flamberge Dragon (UR)

Cosmic Quasar Dragon (UR)
T.G. Glaive Blaster (UR)

Emperor Charles the Great (UR)

Available on February 7th (time zones applying)

-New Selection Pack: Name of Champions
Included cards:
Lady Labrynth of the Silver Castle (UR)

Destiny HERO – Destroyer Phoenix Enforcer (UR)

Baronne de Fleur (UR)

Dingirsu, the Orcust of the Evening Star (UR)

Accesscode Talker (UR)

Available on February 7th (time zones applying)

Furthermore, in regard to the A.I. system, a brief presentation was live streamed on the second day of the event (starts at approximately 47 minutes).

Ken’ichi Kataoka (Master Duel/Duel Links Senior Producer)
Mr. Hattori (Programmer)

Q: Can you provide a basic explanation of what this A.I. project entails?
Mr. Hattori: This project is a system that employs Python for Master Duel. Put simply, with knowledge of A.I. and the Yu-Gi-Oh! OCG, anyone is capable of creating a Duel A.I. that can play Master Duel.
Q: “Anyone” meaning, even someone outside Konami?
Mr. Hattori: Yes, that is accurate. Initially, we would like to observe a Duel between two A.I.s crafted by individuals or groups outside of the Master Duel production team.

The image on the screen essentially illustrates the creation of a specialized interface for the A.I. to directly engage with the game (top image). The text in the middle of both images explains that the operations from the A.I. and the probability evaluations and more form a feedback system. The bottom image explains that it is also possible to utilize a console simulator to conduct Duels at high speed with a text-only interface.

The two squares on the right essentially clarify that information from the Duel and board is organized and distributed to the A.I., which then responds with its inputs and requests. The A.I. agent (written in Python) is an A.I. framework / trained model.

Q: This appears to differ significantly from the typical screen seen in Master Duel, could you provide an overview of what is being depicted?
Mr. Hattori: Yes. Firstly, I would like to draw attention to the percentage at the bottom-left, which indicates the winning odds from the perspective of the moves of the A.I. In this bottom-left box, the total estimated winning odds can be seen, while in the bottom right, we can observe the top 5 moves. Therefore, we will be monitoring the A.I. selecting the #1 move. Currently, the winning odds are low, but eventually, there will be a move that significantly increases the winning odds, so let’s pay close attention to that.

(The A.I. deploys The Melody of Awakening Dragon to search for Blue-Eyes Chaos MAX Dragon and is now able to Ritual Summon it, increasing the winning odds to about 80%)

Q: From my view, it almost seemed like two CPUs Dueling each other, but it’s more than that, correct?
Mr. Hattori: That’s right, these are not CPUs, but rather external programs operating Master Duel. In other words, machine learning is being utilized to train the A.I.. The data of the users is not being utilized at all, and the A.I. is learning from scratch how to Duel by engaging in Duels repeatedly, without even being taught the rules.
Q: By “repeatedly”, approximately how many times would you say?
Mr. Hattori: It has trained in Dueling with the Solo Mode CPU over 100000 times.
Q: Thus, even without being taught the rules, you simply make it Duel over 100000 times, and the outcome is this current A.I.?
Mr. Hattori: Yes. “It has probably played more Duels than humans!”, “That’s some though training!”

Q: There is so much information on the screen, that appears quite captivating!
Mr. Hattori: Yes, we believed it would be intriguing for viewers to display what the A.I. was contemplating on the screen.

Ken’ichi: We are game developers, however, we are not A.I. specialists. Therefore, we thought it would be interesting to see what kind of A.I. could be created by a company that specializes in this field, and what the Duels would be like between these A.I.s, and that’s how we developed this project. “Who can create the strongest A.I.?” Of course, it’s also possible for A.I. to Duel human players, so we would also like to see what the Duels would be like between “the world’s #1 A.I.” and “the champion of the World Championship”.
Q: Thus, an outsider, someone not from Konami, can participate in this as well?
Ken’ichi: Certainly, this is not a system that we will just distribute for everyone to create their own A.I. At this moment, [protocols/rules/terms of service] are being established, and we are presently progressing so that within this year, positions for A.I. Duel creators will be posted at the official Master Duel website.
Mr. Hattori: Initially, we expect the involvement of groups/organizations with A.I. production skills. If feasible, competitions between universities or similar institutions.
“That would be so cool, with each university teaching their own A.I. and then pitting it against other universities!”
Ken’inchi: Yes, the A.I.s created by universities are very fascinating.
“Yes, they have their unique quirks according to who makes them”

Ken’ichi: On the face of it, this conversation has catered mostly to A.I. enthusiasts, but there will also be benefits for all Duelists.
Mr. Hattori: We’ve demonstrated this before in the previous video, but please take a look at this:

Mr. Hattori: By implementing the winning odds estimation function of the A.I., we can create something analogous to the well-known advantage meter from go/shogi.
Q: I understand, so as can be seen in this image, the turn player is in a favorable position, and that is what is being exhibited, correct?
Mr. Hattori: That’s correct. “For us that are commenting on tournaments, you can just look at the screen and figure out who’s winning”, and you might also have a case where someone has like 5% chance of winning, then they draw a new card and boom! They are suddenly able to reverse the odds!

Q: Is there anything else?
Mr. Hattori: Yes, we are also excited about a function that allows you to predict what face-down cards could be. If we could look at the next slide…

Mr. Hattori: Here we can see the A.I. trying to predict what the face-down card could be. [Vaguely explains that the prediction could be off, the A.I. could hold back, move aggressively, etc.]
“It probably got hit by RoD way too many times”
“Whom was it Dueling with those 100000 times?”
“That’s how the A.I. develops its quirks, depending on who it Duels”
“It almost feels like the world of VRAINS, where you can research someone’s Dueling data”

Ken’ichi: The objective of Master Duel is for both participants and spectators to enjoy the Duels. That’s why we are also striving to enhance “what is being shown”. We believe that conveying the best parts of Master Duel in the simplest way possible to those in the audience is a fundamental aspect of increasing the pool of competing players. This is why we continue to evolve Master Duel for Duelists and those cheering on those Duelists. Stay tuned for the future of Yu-Gi-Oh digital games!

A live demonstration then commences. Both Ken’ichi and Mr. Hattori quickly mention that while the A.I. has Duelt over 100000 times, it is still considered “young” and “underdeveloped” in terms of A.I., so it may still make some unexpected moves. Mr. Hattori highlights that when the A.I. is about to attack and the opponent controls a face-down card, it’s making a decision based on potential face-down cards, and once it decides that it’s not a threat (Eternal Soul instead of Mirror Force), it proceeds with the attack. He also highlights that the A.I. comprehends some understanding of the opponent’s Deck in order to make such predictions. Mr. Hattori is asked if it’s possible to teach the A.I. about the existence of certain Decks so that it learns how to deal with them, for example, taking a presently strong Deck, like “Horus”, and teaching it to the A.I., and Mr. Hattori responds it is plausible to teach the A.I. that way. The A.I. deploys Ring of Destruction during the End Phase, and when Mr. Hattori is questioned about whether this particular use of the card was learned by the A.I., he explains that through thousands of Duels, the A.I. has a high valuation of moves that lead to victory. While the A.I. does not know the rules of Yu-Gi-Oh, it understands that this particular move leads to positive results.

(The Duel unfortunately ends prematurely due to time constraints)

Leave a Reply

Your email address will not be published. Required fields are marked *