Talk:1002: Game AIs - Revision history

208.59.176.206: comment

2026-01-05T00:38:55Z

comment

799571388 at 11:40, 14 February 2025

2025-02-14T11:40:17Z

Hhhguir at 07:33, 6 October 2024

2024-10-06T07:33:56Z

172.71.242.160 at 19:04, 3 March 2024

2024-03-03T19:04:55Z

162.158.159.132: Game of Life missing?

2024-03-03T17:24:56Z

Game of Life missing?

172.70.162.147 at 13:09, 12 February 2022

2022-02-12T13:09:49Z

162.158.155.36: Clarify the complexity of Mao in discussion

2020-08-29T21:51:32Z

Clarify the complexity of Mao in discussion

172.68.38.44 at 01:21, 26 July 2020

2020-07-26T01:21:46Z

172.68.38.44 at 01:21, 26 July 2020

2020-07-26T01:21:18Z

172.68.38.44 at 01:21, 26 July 2020

2020-07-26T01:21:04Z

@@ Line 53: / Line 53: @@
 :That's (as I suspected) a disambiguation page, making me still wonder whether you mean {{w|Conway's Game of Life}} (which is a bit open-ended) or ''{{w|The Game of Life}}'' (which, if I remember the gameplay well enough is basically going to be the same luck-based-'challenge' as Snakes And Ladders with an expanded set of thematic bells-and-whistles added).
 :Such a confluence of names, however, makes me want to suggest {{w|Mastermind (board game)}} (well within 'solved' for just brute-force logic) or {{w|Mastermind (British game show)}} (you'd definitely need a Watson-level AI, though you probably you could zhoosh it up with a ChatGPT front-end). [[Special:Contributions/172.71.242.160|172.71.242.160]] 19:04, 3 March 2024 (UTC)
 I'm a little late to say this, but '''Update for Go:''' In early 2023, Kellin Pelrine defeated KataGo and Leela Zero, not by being a top player, but by employing an unusual strategy that the AIs couldn't detect, even though most human players could. (Admittedly, the strategy itself was found by yet another AI). [https://arstechnica.com/information-technology/2023/02/man-beats-machine-at-go-in-human-victory-over-ai/] [https://www.pcgamer.com/a-human-has-beat-an-ai-in-possibly-the-most-complex-board-game-ever/] [[User:Hhhguir|Hhhguir]] ([[User talk:Hhhguir|talk]]) 07:33, 6 October 2024 (UTC)
 Update: Now 'AI' (well, LLM actually) learns to cheat playing chess [[User:799571388|799571388]] ([[User talk:799571388|talk]]) 11:40, 14 February 2025 (UTC)

← Older revision		Revision as of 11:40, 14 February 2025
Line 55:		Line 55:

	I'm a little late to say this, but '''Update for Go:''' In early 2023, Kellin Pelrine defeated KataGo and Leela Zero, not by being a top player, but by employing an unusual strategy that the AIs couldn't detect, even though most human players could. (Admittedly, the strategy itself was found by yet another AI). [https://arstechnica.com/information-technology/2023/02/man-beats-machine-at-go-in-human-victory-over-ai/] [https://www.pcgamer.com/a-human-has-beat-an-ai-in-possibly-the-most-complex-board-game-ever/] [[User:Hhhguir\|Hhhguir]] ([[User talk:Hhhguir\|talk]]) 07:33, 6 October 2024 (UTC)		I'm a little late to say this, but '''Update for Go:''' In early 2023, Kellin Pelrine defeated KataGo and Leela Zero, not by being a top player, but by employing an unusual strategy that the AIs couldn't detect, even though most human players could. (Admittedly, the strategy itself was found by yet another AI). [https://arstechnica.com/information-technology/2023/02/man-beats-machine-at-go-in-human-victory-over-ai/] [https://www.pcgamer.com/a-human-has-beat-an-ai-in-possibly-the-most-complex-board-game-ever/] [[User:Hhhguir\|Hhhguir]] ([[User talk:Hhhguir\|talk]]) 07:33, 6 October 2024 (UTC)
		+
		+	Update: Now 'AI' (well, LLM actually) learns to cheat playing chess [[User:799571388\|799571388]] ([[User talk:799571388\|talk]]) 11:40, 14 February 2025 (UTC)

← Older revision		Revision as of 07:33, 6 October 2024
Line 53:		Line 53:
	:That's (as I suspected) a disambiguation page, making me still wonder whether you mean {{w\|Conway's Game of Life}} (which is a bit open-ended) or ''{{w\|The Game of Life}}'' (which, if I remember the gameplay well enough is basically going to be the same luck-based-'challenge' as Snakes And Ladders with an expanded set of thematic bells-and-whistles added).		:That's (as I suspected) a disambiguation page, making me still wonder whether you mean {{w\|Conway's Game of Life}} (which is a bit open-ended) or ''{{w\|The Game of Life}}'' (which, if I remember the gameplay well enough is basically going to be the same luck-based-'challenge' as Snakes And Ladders with an expanded set of thematic bells-and-whistles added).
	:Such a confluence of names, however, makes me want to suggest {{w\|Mastermind (board game)}} (well within 'solved' for just brute-force logic) or {{w\|Mastermind (British game show)}} (you'd definitely need a Watson-level AI, though you probably you could zhoosh it up with a ChatGPT front-end). [[Special:Contributions/172.71.242.160\|172.71.242.160]] 19:04, 3 March 2024 (UTC)		:Such a confluence of names, however, makes me want to suggest {{w\|Mastermind (board game)}} (well within 'solved' for just brute-force logic) or {{w\|Mastermind (British game show)}} (you'd definitely need a Watson-level AI, though you probably you could zhoosh it up with a ChatGPT front-end). [[Special:Contributions/172.71.242.160\|172.71.242.160]] 19:04, 3 March 2024 (UTC)
		+
		+	I'm a little late to say this, but '''Update for Go:''' In early 2023, Kellin Pelrine defeated KataGo and Leela Zero, not by being a top player, but by employing an unusual strategy that the AIs couldn't detect, even though most human players could. (Admittedly, the strategy itself was found by yet another AI). [https://arstechnica.com/information-technology/2023/02/man-beats-machine-at-go-in-human-victory-over-ai/] [https://www.pcgamer.com/a-human-has-beat-an-ai-in-possibly-the-most-complex-board-game-ever/] [[User:Hhhguir\|Hhhguir]] ([[User talk:Hhhguir\|talk]]) 07:33, 6 October 2024 (UTC)

← Older revision		Revision as of 19:04, 3 March 2024
Line 51:		Line 51:

	If Snakes and Ladders and Seven Minutes in Heaven are mentioned, why not [[wikipedia:Game of Life\|Game of Life]]? --[[Special:Contributions/162.158.159.132\|162.158.159.132]] 17:24, 3 March 2024 (UTC)		If Snakes and Ladders and Seven Minutes in Heaven are mentioned, why not [[wikipedia:Game of Life\|Game of Life]]? --[[Special:Contributions/162.158.159.132\|162.158.159.132]] 17:24, 3 March 2024 (UTC)
		+	:That's (as I suspected) a disambiguation page, making me still wonder whether you mean {{w\|Conway's Game of Life}} (which is a bit open-ended) or ''{{w\|The Game of Life}}'' (which, if I remember the gameplay well enough is basically going to be the same luck-based-'challenge' as Snakes And Ladders with an expanded set of thematic bells-and-whistles added).
		+	:Such a confluence of names, however, makes me want to suggest {{w\|Mastermind (board game)}} (well within 'solved' for just brute-force logic) or {{w\|Mastermind (British game show)}} (you'd definitely need a Watson-level AI, though you probably you could zhoosh it up with a ChatGPT front-end). [[Special:Contributions/172.71.242.160\|172.71.242.160]] 19:04, 3 March 2024 (UTC)

← Older revision		Revision as of 17:24, 3 March 2024
Line 49:		Line 49:
	* Machine-vision is a thing. I'm sure there's a trivial way to make a generalised board-image-decoder to get around the artistic differences (possibly even machine learning, to make actual use of the AI).		* Machine-vision is a thing. I'm sure there's a trivial way to make a generalised board-image-decoder to get around the artistic differences (possibly even machine learning, to make actual use of the AI).
	....The main issue is that solving all these 'problems' leaves little for the backend 'gameplay and strategy' AI to do, as it must just pursue the path to victory (or not) that the dice/whatever formulaically dictate. So I want to honour the edit by mentioning it, but ultimately decided it should be undone. Pending perhaps a different approach to it, if anyone decides I was not fair (or correct) in my decision to do it this way. [[Special:Contributions/172.70.162.147\|172.70.162.147]] 13:09, 12 February 2022 (UTC)		....The main issue is that solving all these 'problems' leaves little for the backend 'gameplay and strategy' AI to do, as it must just pursue the path to victory (or not) that the dice/whatever formulaically dictate. So I want to honour the edit by mentioning it, but ultimately decided it should be undone. Pending perhaps a different approach to it, if anyone decides I was not fair (or correct) in my decision to do it this way. [[Special:Contributions/172.70.162.147\|172.70.162.147]] 13:09, 12 February 2022 (UTC)
		+
		+	If Snakes and Ladders and Seven Minutes in Heaven are mentioned, why not [[wikipedia:Game of Life\|Game of Life]]? --[[Special:Contributions/162.158.159.132\|162.158.159.132]] 17:24, 3 March 2024 (UTC)

← Older revision		Revision as of 13:09, 12 February 2022
Line 43:		Line 43:
	I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.		I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.
	: The tricky part is that rules in Mao aren't limited to a function that states whether or not you can play a card based on the cards already played. Rules can be about how you play the card, how you sit, what you say, what you do if you play a certain card, etc. Rules can also apply out of turn. You could be required to do something in reaction to another player doing something (e.g. congratulate a player if they play a King), or penalised for e.g. speaking to the player whose turn it currently is. In order for a computer to compete successfully, it would need to ingest a lot of peripheral information and run some sophisticated learning that accounts for far more than simply the state of the cards. Particularly within a regular group of players, there are rules that will be reused a lot, e.g. certain cards acting as Uno special cards, but there is no guarantee these will appear and players can make up arbitrary rules. --Tom		: The tricky part is that rules in Mao aren't limited to a function that states whether or not you can play a card based on the cards already played. Rules can be about how you play the card, how you sit, what you say, what you do if you play a certain card, etc. Rules can also apply out of turn. You could be required to do something in reaction to another player doing something (e.g. congratulate a player if they play a King), or penalised for e.g. speaking to the player whose turn it currently is. In order for a computer to compete successfully, it would need to ingest a lot of peripheral information and run some sophisticated learning that accounts for far more than simply the state of the cards. Particularly within a regular group of players, there are rules that will be reused a lot, e.g. certain cards acting as Uno special cards, but there is no guarantee these will appear and players can make up arbitrary rules. --Tom
		+
		+	Sorry, but I just undid a new editor's addition of the text (for Snakes And Ladders) of "except that as the game has to be played on software so that an AI can participate, a (pseudo)-random number generator takes the place of physical dice in dictating players' movement, making it no longer truly random. Also, while physical snakes-and-ladders boards are fixed in their design, the graphical representation of these boards can be altered at will." - Firstly because it was bullet-point-added, when it wasn't really supposed to be, but then I decided it needed much more editing than I thought worthwhile. To bullet my thoughts, though:
		+	* See the Beer Pong example for "AI in reality",
		+	* Even if there's not a robot arm shaking a physical dice (which is pseudorandom itself, at least in a Newtonian perspective, but tends to be Ok) as long as the supposed-PRNG is not controlled/filtered by the AI then it's perfectly valid for use,
		+	* Machine-vision is a thing. I'm sure there's a trivial way to make a generalised board-image-decoder to get around the artistic differences (possibly even machine learning, to make actual use of the AI).
		+	....The main issue is that solving all these 'problems' leaves little for the backend 'gameplay and strategy' AI to do, as it must just pursue the path to victory (or not) that the dice/whatever formulaically dictate. So I want to honour the edit by mentioning it, but ultimately decided it should be undone. Pending perhaps a different approach to it, if anyone decides I was not fair (or correct) in my decision to do it this way. [[Special:Contributions/172.70.162.147\|172.70.162.147]] 13:09, 12 February 2022 (UTC)

← Older revision		Revision as of 21:51, 29 August 2020
Line 42:		Line 42:

	I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.		I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.
		+	: The tricky part is that rules in Mao aren't limited to a function that states whether or not you can play a card based on the cards already played. Rules can be about how you play the card, how you sit, what you say, what you do if you play a certain card, etc. Rules can also apply out of turn. You could be required to do something in reaction to another player doing something (e.g. congratulate a player if they play a King), or penalised for e.g. speaking to the player whose turn it currently is. In order for a computer to compete successfully, it would need to ingest a lot of peripheral information and run some sophisticated learning that accounts for far more than simply the state of the cards. Particularly within a regular group of players, there are rules that will be reused a lot, e.g. certain cards acting as Uno special cards, but there is no guarantee these will appear and players can make up arbitrary rules. --Tom

@@ Line 34: / Line 34: @@
 AlphaStar beat Mana pretty decisively, but it was cheating and Mana won the game where it wasn't, and it could only play on a certain map in Protoss vs Protoss. However, that was a while ago. Google dropped AlphaStar on ladder under barcode usernames, and it's been doing rather well... but Serral (one of the world's best players) recently beat it pretty decisively. [[Special:Contributions/172.68.211.244|172.68.211.244]] 01:49, 19 September 2019 (UTC)
 Who is Ken Jennings?
 I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.

@@ Line 41: / Line 41: @@
 :In case anyone is checking up on the AlphaStar thing: AlphaStar definitely plays at a high human level in Starcraft 2 now (2020), without doing much that seems 'humanly impossible' (ie, like cheating, as it did during the MaNa matchup), but it's in relatively limited maps, and it not only loses fairly regularly if not most of the time to top-ranked humans like Serral, it also loses to essentially random grab-bags of very good players like Lowko on occasion. Like, Lowko's much better than me but he's not tournament-level good and he beat it.
 :Also, technically, AlphaStar isn't even *one* program. It's an ensemble of many programs, each one specific to a different SC2 race and specializing in different strategies. Maybe if there were a 'seamless' amalgam where it were 'choosing' a strategy it could be arguably one program, but it's literally a totally separately trained neural network for each 'agent'.
-:Furthermore, when you watch it play sometimes it does extremely stupid things like trap its tanks in its own base. SC2 is, at least this year, still a human endeavor at high tiers.
+:Furthermore, when you watch it play sometimes it does extremely stupid things like trap its tanks in its own base. SC2 is, at least this year, still a human endeavor at high tiers. [[Special:Contributions/172.68.38.44|172.68.38.44]] 01:21, 26 July 2020 (UTC)

← Older revision		Revision as of 01:21, 26 July 2020
Line 38:		Line 38:

	I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.		I feel like it should be relatively easy to make a computer program that can learn the rules of Mao without knowing them to begin with. There has to be some feedback: a player gets penalties if he breaks the rules. This can be used to write a self-learning algorithm.
		+
		+	:In case anyone is checking up on the AlphaStar thing: AlphaStar definitely plays at a high human level in Starcraft 2 now (2020), without doing much that seems 'humanly impossible' (ie, like cheating, as it did during the MaNa matchup), but it's in relatively limited maps, and it not only loses fairly regularly if not most of the time to top-ranked humans like Serral, it also loses to essentially random grab-bags of very good players like Lowko on occasion. Like, Lowko's much better than me but he's not tournament-level good and he beat it.
		+	:Also, technically, AlphaStar isn't even one program. It's an ensemble of many programs, each one specific to a different SC2 race and specializing in different strategies. Maybe if there were a 'seamless' amalgam where it were 'choosing' a strategy it could be arguably one program, but it's literally a totally separately trained neural network for each 'agent'.
		+	:Furthermore, when you watch it play sometimes it does extremely stupid things like trap its tanks in its own base. SC2 is, at least this year, still a human endeavor at high tiers.