Skip to main content
5 votes

How can I design and train a neural network to play a card game (similar to Magic: The Gathering)?

Yes. It is feasible. Overview of the Question The design goal of the system seems to be gain a winning strategic advantage by employing one or more artificial networks in conjunction with a card ...
Douglas Daseeco's user avatar
5 votes

How can I design and train a neural network to play a card game (similar to Magic: The Gathering)?

I think you raise a good question, especially WRT to how the NNs inputs & outputs are mapped onto the mechanics of a card game like MtG where the available actions vary greatly with context. I ...
Ben Hutchison's user avatar
4 votes

How can I design and train a neural network to play a card game (similar to Magic: The Gathering)?

This is completely feasible, but the way the inputs are mapped would greatly depend on the type of card game, and how it's played. I'll take into account a few possibilities: Does time matter in ...
TajyMany's user avatar
  • 166
2 votes

How can I design and train a neural network to play a card game (similar to Magic: The Gathering)?

You would definitely want your network to know crucial information about the game, like what cards AI agent has(their values and types), mana pool, how many cards on the table and their values, number ...
Andrew's user avatar
  • 276
1 vote

Monte Carlo Tree Search for trick taking games, such as Whist, Bridge

In general, the solution concept of imperfect-information games is more complicated than games with perfect information. This is due to the neccesity of randomizing your own actions: e.g. in the rock-...
Jakub Koubele's user avatar
1 vote

Monte Carlo Tree Search for Robo Rally AI

Have looked at the game description. MCTS can be a very good choice, as far as I can tell. The action that you take at each phase is selecting five cards from the nine you have and placing them face ...
Oren's user avatar
  • 141
1 vote

Could a good poker-playing AI be made that didn't look at its own cards?

If the AI does not know its own cards, it only has less knowledge and is therefore at a disadvantage. The AI could only act on the basis of the other players' play, while they know their own cards and ...
dexteritas's user avatar
1 vote
Accepted

How should I write the reward function to teach the agent the rules of this card game?

I would recommend having the reward as the increase to score caused by adding the card in the chosen location. You could optionally include calculations based on partial rows for pairs, three-of-a-...
Neil Slater's user avatar
  • 32.1k
1 vote

How can I design and train a neural network to play a card game (similar to Magic: The Gathering)?

I'm not sure if or how I would apply neural networks to make selections with cards, which have a complex synergy. How could I design and train a neural network for this game, such that it can take ...
Eugen Bondarev's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible