# Can ai's play boardgames? **URL:** \ **Category:** Factual Questions\ **Tags:** board-card-word-game, chess, ai\ **Created:** [April 20, 2026, 2:27pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428 "2026-04-20T14:27:13Z")\ **Posts on this page:** 20\ **Page:** 2
**Author:** ![RitterSport](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/rittersport/32/6326_2.png) [@RitterSport](https://boards.straightdope.com/u/RitterSport)\ **Post date:** [April 20, 2026, 3:22pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/21 "2026-04-20T15:22:25Z")
It’s beating me so far. I’m not going to continue playing – more of a proof of concept. It’s keeping track of the scoresheets and it has a mechanism to pick the dice you want to hang on to. So, that’s one game an AI can play without any problems. ---
**Author:** ![Maserschmidt](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/maserschmidt/32/18829_2.png) [@Maserschmidt](https://boards.straightdope.com/u/Maserschmidt)\ **Post date:** [April 20, 2026, 3:24pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/22 "2026-04-20T15:24:06Z")
> [@Jas09](#): > > That said, thinks like AlphaGo and AlphaZero show that a neural-net framework that is only fed the rules of the game and then just learns how to play organically can easily beat human players at any game. Since this is FQ: AlphaGo (the specific instance of AlphaZero used for Go) was given expert games as part of its training; the AlphaZero instance of chess was not. Both models also used self-play. ---
**Author:** ![Dorjan](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/dorjan/32/12440_2.png) [@Dorjan](https://boards.straightdope.com/u/Dorjan)\ **Post date:** [April 20, 2026, 3:25pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/23 "2026-04-20T15:25:23Z")
If there is an online version of a game available, it would be a lot easier to take screenshots of the game progress than photos of an actual gameboard. I think i will give it a shot with Gemini later this eve. Game TBD, maybe Risk! That would be fun. Or Scrabble. I’m interested to see if it would start making up words based on the tiles that it has. ---
**Author:** ![Left\_Hand\_of\_Dorkness](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/left_hand_of_dorkness/32/7156_2.png) [@Left\_Hand\_of\_Dorkness](https://boards.straightdope.com/u/Left_Hand_of_Dorkness)\ **Post date:** [April 20, 2026, 3:28pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/24 "2026-04-20T15:28:26Z")
Here’s a Catan Clone called “Colonists” that’s free and online, with rules available. > **[More](https://colonist.io/more)** > > More ---
**Author:** ![Little\_Nemo](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/little_nemo/32/3120_2.png) [@Little\_Nemo](https://boards.straightdope.com/u/Little_Nemo)\ **Post date:** [April 20, 2026, 3:28pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/25 "2026-04-20T15:28:38Z")
> [@Jas09](#): > > What AI specifically are you asking about? There is no single “AI” that we can answer this question about. I think it’s obvious I know very little about ai’s. ---
**Author:** ![Little\_Nemo](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/little_nemo/32/3120_2.png) [@Little\_Nemo](https://boards.straightdope.com/u/Little_Nemo)\ **Post date:** [April 20, 2026, 3:37pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/26 "2026-04-20T15:37:47Z")
> [@Jas09](#): > > Honestly for almost all games the level of complexity is so low that a specific-built program for just that ruleset is more than enough to beat any human player. It’s only for very “deep” strategy games like Chess and Go that this has been a hard problem for computers until the last few decades. I think Chess or Go would be considered fairly medium weight games in modern board gaming. They just have a sense of historical mystique. But Chess and Go aren’t really any more complex than games like Onitama or Hive and nobody is calling those heavy weight games. I feel an ai would have a lot more difficulty in a game like Arkwright or Feudum or Hegemony. ---
**Author:** ![CaveMike](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/cavemike/32/16379_2.png) [@CaveMike](https://boards.straightdope.com/u/CaveMike)\ **Post date:** [April 20, 2026, 3:42pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/27 "2026-04-20T15:42:48Z")
> [@Little\_Nemo](#): > > Yes but I’m assuming a human had to “teach” AlphaZero the rules of chess first. [MuZero](https://en.wikipedia.org/wiki/MuZero) is a successor to AlphaZero that learns to play games without rules. AlphaZero learned to play chess, shogi, and go through self-play. > **MuZero** is a [computer program](https://en.wikipedia.org/wiki/Computer_program) developed by [artificial intelligence](https://en.wikipedia.org/wiki/Artificial_intelligence) research company [DeepMind](https://en.wikipedia.org/wiki/DeepMind), a subsidiary of [Google](https://en.wikipedia.org/wiki/Google), to master games without knowing their rules and underlying dynamics. > MuZero was trained via [self-play](https://en.wikipedia.org/wiki/Self-play_(reinforcement_learning_technique)), with no access to rules, opening books, or endgame tablebases. The trained algorithm used the same convolutional and residual architecture as AlphaZero, but with 20 percent fewer computation steps per node in the search tree. ---
**Author:** ![CaveMike](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/cavemike/32/16379_2.png) [@CaveMike](https://boards.straightdope.com/u/CaveMike)\ **Post date:** [April 20, 2026, 4:01pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/28 "2026-04-20T16:01:04Z")
> [@Left\_Hand\_of\_Dorkness](#): > > Has anyone actually tried this experiment? I’d be moderately surprised if the AI could accurately interpret photographs of the board, and very surprised if the AI could play effectively, just from reading the PDF of the rules. I’ve been working on this as a fun project with the goal of creating a tool to prototype board games and mechanics. Rather than giving it images of the game or a PDF of the rules, I have a game engine that plays the game and enforces the rules. The Player or Bot just gets a set of valid choices and the game’s state. The dumbest Bot picks a random choice. My intention was to use Reinforcement Learning to create an ML/AI Bot, but I haven’t gotten to that part. Recently I have been trying to use an LLM to generate code for the Bot with (so far) not so great results. There are AIs that can play Atari games using just the screen contents. In one of Andrej Karpathy’s Standford class sessions he creates a simple AI to play Atari Breakout. It is a pretty short implementation and you can follow along and build your own. So going from valid choices to a picture of the board game is possible, but more computational expensive. ---
**Author:** ![CaveMike](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/cavemike/32/16379_2.png) [@CaveMike](https://boards.straightdope.com/u/CaveMike)\ **Post date:** [April 20, 2026, 4:10pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/29 "2026-04-20T16:10:50Z")
> [@Little\_Nemo](#): > > I think Chess or Go would be considered fairly medium weight games in modern board gaming. They just have a sense of historical mystique. > > But Chess and Go aren’t really any more complex than games like Onitama or Hive and nobody is calling those heavy weight games. My kids and I were discussing this topic recently. Abstract board games, like Chess and Go, might be medium-weight in rules, but not necessarily in optimal game play. I assume Onitama and Hive as well, but I am not familiar with them. [Heavy-weight, non-abstract games](https://boardgamegeek.com/geeklist/188270/the-heaviest-games-on-the-geek) might have more choices and complexity, but they are more prone to being less balanced. There can be decision paths that are clearly better or worse and an AI can learn these paths quickly. ---
**Author:** ![glee](https://avatars.discourse-cdn.com/v4/letter/g/b5a626/32.png) [@glee](https://boards.straightdope.com/u/glee)\ **Post date:** [April 20, 2026, 4:11pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/30 "2026-04-20T16:11:39Z")
> [@Dorjan](#): > > Chess is not a simple board game, so I don’t think that’s a fair comparison. There’s a lot more long-term strategy involved. As an experienced chess coach, I can say two things: - it’s easy to teach ‘how to play chess’ … there are only 6 pieces, plus a few special moves (e.g. castling) - chess strategy and tactics make it a deep complicated game to do well at … however since it’s a logical, full information game, it’s ideal for computers to pick up and excel at ---
**Author:** ![md-2000](https://avatars.discourse-cdn.com/v4/letter/m/9d8465/32.png) [@md-2000](https://boards.straightdope.com/u/md-2000)\ **Post date:** [April 20, 2026, 4:58pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/31 "2026-04-20T16:58:45Z")
> [@glee](#): > > As an experienced chess coach, I can say two things: > > - it’s easy to teach ‘how to play chess’ … there are only 6 pieces, plus a few special moves (e.g. castling) > - chess strategy and tactics make it a deep complicated game to do well at … however since it’s a logical, full information game, it’s ideal for computers to pick up and excel at This is part of the discussion that needs to be explicit - the rules are “what is a valid, legal move?” and “how does one win?”. Strategy is what makes a player (real or AI) good. Part of strategy is understanding what an opponent could do in response. > [@CaveMike](#): > > [MuZero](https://en.wikipedia.org/wiki/MuZero) is a successor to AlphaZero that learns to play games without rules. AlphaZero learned to play chess, shogi, and go through self-play. I assume with the “not told the rules” version of AI, there is still a supervisor validating any moves. Otherwise the result would just be decorating the chessboard randomly. So it is being told the rules by inference. After a thousand games, an AI might enocunter and figure out all the rules and limitations of, say, castling. I presume the supervisor does not say “you cannot castle through check” or any other hint, simply says “move not allowed”. ---
**Author:** ![CaveMike](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/cavemike/32/16379_2.png) [@CaveMike](https://boards.straightdope.com/u/CaveMike)\ **Post date:** [April 20, 2026, 5:06pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/32 "2026-04-20T17:06:49Z")
> [@md-2000](#): > > I assume with the “not told the rules” version of AI, there is still a supervisor validating any moves. That is my assumption as well. In chess engines there are various formats for encoding the legal moves at any given step. I think this is the input to the AI and the output is one of those moves. ---
**Author:** ![Little\_Nemo](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/little_nemo/32/3120_2.png) [@Little\_Nemo](https://boards.straightdope.com/u/Little_Nemo)\ **Post date:** [April 20, 2026, 5:38pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/33 "2026-04-20T17:38:50Z")
> [@md-2000](#): > > I assume with the “not told the rules” version of AI, there is still a supervisor validating any moves. Otherwise the result would just be decorating the chessboard randomly. So it is being told the rules by inference. After a thousand games, an AI might enocunter and figure out all the rules and limitations of, say, castling. I presume the supervisor does not say “you cannot castle through check” or any other hint, simply says “move not allowed”. I can see this process of learning by self-play working in chess, where you have thirty-two pieces on a sixty-four square board and a single winning objective. A fast computer can play the game millions of times and develop paths that will lead to winning. But would this process work in a game like Bridge, for example? Suppose an ai was “playing” a hand of thirteen cards, with no programmed idea what the rules are. So it plays a random card. The other players, human or ai, play cards as well and then the judge informs the table who won the trick. An ai playing the same hand over and over again would eventually learn which cards win the trick and which cards lose. If you had a _really_ long time, it would eventually learn what order to play all thirteen cards in to produce the highest total of wins. (To give an idea how long this would take, each player has thirteen cards, which means there are over six billion different ways those cards can be played. And to determine which way is optimal, you would have to compare each of those six billion ways to each of the six billion ways the other three players could possibly play their hands. Over 1,300,000,000,000,000,000,000,000,000,000,000,000,000,000 plays if my quick calculations are correct.) But at the end of these tredecillion plays, the ai will have learned the optimal way to play this hand. And will be ready for the new deal, which will be completely different. ---
**Author:** ![Maserschmidt](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/maserschmidt/32/18829_2.png) [@Maserschmidt](https://boards.straightdope.com/u/Maserschmidt)\ **Post date:** [April 20, 2026, 5:50pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/34 "2026-04-20T17:50:48Z")
I don’t have an opinion on whether bridge is workable, I’d just note that every hand opens with bidding in which your bid is often communicating things to your partner that may sound like that bid at all (i.e. conventions), I’m not sure how that part would work. But I’d love if it came up with new conventions somehow. ETA also, the bidding of your opponents can inform the optimal play of your hand. So there’s that as well. ---
**Author:** ![N9IWP](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/n9iwp/32/3154_2.png) [@N9IWP](https://boards.straightdope.com/u/N9IWP)\ **Post date:** [April 20, 2026, 5:56pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/35 "2026-04-20T17:56:51Z")
I think the trading aspect of Catan might be the hardest part. Wonder if you started with no luck (other than initial set up) games like [Caylus](https://boardgamegeek.com/boardgame/18602/caylus) (initial turn order, and order of pink buildings) or [Ora & Labora](https://boardgamegeek.com/boardgame/70149/ora-et-labora) (initial turn order, and whether it is Ireland or France) would be easier. [Puerto Rico](https://boardgamegeek.com/boardgame/3076/puerto-rico) has a smidge of randomness (which plantations come out) Brian ---
**Author:** ![Sitnam](https://avatars.discourse-cdn.com/v4/letter/s/6a8cbe/32.png) [@Sitnam](https://boards.straightdope.com/u/Sitnam)\ **Post date:** [April 20, 2026, 6:08pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/36 "2026-04-20T18:08:32Z")
I love board games and use AI for rules questions all the time. It is not entirely clear to me AI understands any game much less possess the ability for optimal moves or an understanding of game state. ---
**Author:** ![Left\_Hand\_of\_Dorkness](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/left_hand_of_dorkness/32/7156_2.png) [@Left\_Hand\_of\_Dorkness](https://boards.straightdope.com/u/Left_Hand_of_Dorkness)\ **Post date:** [April 20, 2026, 7:00pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/37 "2026-04-20T19:00:09Z")
> [@N9IWP](#): > > I think the trading aspect of Catan might be the hardest part. Far harder than for a human. With my daughter, she started beating me at Catan while still in elementary school (with a bit of coaching on good strategy). Could an AI figure out how to make effective trades? And the conversation about playing the game billions of times is, I think, missing the question. The question is what happens when you follow these steps: 1. “Hey GemiClaudeGPT, we’re going to play Catan! I’m going to upload a PDF of the rules, and after each turn I’ll show you a photograph of the board position. We’ll use this online dice roller.” 2. “Now that you’ve read the rules, here’s a picture of the board setup. Tell me where you want to place your initial pieces, and I’ll put them down for you.” 3. “Let’s start play! Here’s the first roll of the dice. Your turn: what do you do?” ---
**Author:** ![glee](https://avatars.discourse-cdn.com/v4/letter/g/b5a626/32.png) [@glee](https://boards.straightdope.com/u/glee)\ **Post date:** [April 20, 2026, 7:02pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/38 "2026-04-20T19:02:06Z")
[quote=“Little\_Nemo, post:33, topic:1029428”] A fast computer can play the game millions of times and develop paths that will lead to winning. … But would this process work in a game like Bridge, for example? [/quote].. There is already a computer program (Deep Finesse) that gives the maximum possible tricks for each hand: > [@Little\_Nemo](#): > > each player has thirteen cards, which means there are over six billion different ways those cards can be played Does it help simplify the numbers that players have to follow suit? (i.e if a club is led, everyone must play a club if they can…) ---
**Author:** ![RitterSport](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/rittersport/32/6326_2.png) [@RitterSport](https://boards.straightdope.com/u/RitterSport)\ **Post date:** [April 20, 2026, 7:08pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/39 "2026-04-20T19:08:46Z")
I doubt there’s a game on the planet that Claude doesn’t already know the rules to. If you want, I can DM you a link that shows a few back-and-forth interactions I had with Claude on Catan. I’ve never played it, so I don’t know if it’s making sense. Claude is free for a fair number of interactions. Just give it a try, it won’t bite (unless you specifically request that, and hook up a remote biting robot). ---
**Author:** ![Great\_Antibob](https://avatars.discourse-cdn.com/v4/letter/g/e47c2d/32.png) [@Great\_Antibob](https://boards.straightdope.com/u/Great_Antibob)\ **Post date:** [April 20, 2026, 7:19pm UTC](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428/40 "2026-04-20T19:19:18Z")
That’s still fighting the hypothetical. What if it were a game I had just invented and happened to have made a PDF of the rules that are not available anywhere else? Note, I think some "AI"s (again something that’s not quite well defined) would be able to figure some things out but it would be a different beast from a well known game that’s been out there for a while [Previous page](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428.md?page=1) [Next page](https://boards.straightdope.com/t/can-ais-play-boardgames/1029428.md?page=3)