MuZero: Mastering Go, chess, shogi and Atari without rules
1–10 of 79 posts
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#2Same topic as a year ago, but deserves much more examination than it got then.
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#3Whoa, this is extremely impressive. Quotes from the BBC article:
> "For the first time, we actually have a system which is able to build its own understanding of how the world works, and use that understanding to do this kind of sophisticated look-ahead planning that you've previously seen for games like chess.
> "[It] can start from nothing, and just through trial and error both discover the rules of the world and use those rules to achieve kind of superhuman performance."
> [...] MuZero is effectively able to squeeze out more insight from less data than had been possible before, explained Dr Silver.
https://www.bbc.com/news/technology-55403473
It seems like we're getting much closer to artificial general intelligence from two directions: reinforcement learning (such as MuZero), and sequence prediction (such as GPT-3 and iGPT). Very interesting times to be in the AI field.
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#4Amazing! Anyone has ideas on how to: 1. Bet on AGI, 2. Encourage AGI?
I have a strong belief that it could grow and I’d like to contribute (and join the development)
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#5Is there a way to learn Go from scratch using these AIs? I wonder if it would pay off in the long run to be fully trained by one.
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#6Is there a way to learn Go from scratch using these AIs? I wonder if it would pay off in the long run to be fully trained by one.
I think it would just smoke you from the outset. As far as I know it doesn't have a structured intelligence it can scale back - it would make the optimal move every time, destroying you like it destroyed top-tier players.
I tried learning Go a little while back but hit a wall. Was thinking about trying this more gamified option:
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#7Amazing! Anyone has ideas on how to: 1. Bet on AGI, 2. Encourage AGI? I have a strong belief that it could grow and I’d like to contribute (and join the development)
It's not obvious this has much to do with AGI in the sense of human level sentience.
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#8Is there a way to learn Go from scratch using these AIs? I wonder if it would pay off in the long run to be fully trained by one.
I think it would just smoke you from the outset. As far as I know it doesn't have a structured intelligence it can scale back - it would make the optimal move every time, destroying you like it destroyed top-tier players. I tried learning Go a little while back but hit a wall. Was thinking about trying this more gamified option: https://www.wolfeystudios.com/TheConquestOfGo.html
My rudimentary understanding of most reinforcement learning systems is that there is an "probability of optimality" associated with each action. Wouldn't there be a way to make the AI take the Nth optimal move or vary the degree of optimality with each move?
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#9Whoa, this is extremely impressive. Quotes from the BBC article: > "For the first time, we actually have a system which is able to build its own understanding of how the world works, and use that understanding to do this kind of sophisticated look-ahead planning that you've previously seen for games like chess. > "[It] can start from nothing, and just through trial and error both discover the rules of the world and u…
I've noticed all the top performing AI reinforcement algorithms i hear about know next to nothing about the initial rules. And not only do they perform as well as more supervised methods, but much better
The one exception is self driving. I listened to the Lex Fridman interview with ceo of waymo recently and he made a case for the controlled environment (e.g. separate detection from decision making and planning) and pushed back against the end to end approach that doesn't make any preconceived assumptions about the environment. As an example he takes red lights. They're clearly human engineered signals, so it makes sense to have a module that can explicitly determine the signal as opposed to learning the behavior
But that's true about other games as well and end to end methods still outperform. Which makes me ask, is end to end learning an inevitability for self driving as well or is this the one domain special due to complexity or other aspects?
Re: MuZero: Mastering Go, chess, shogi and Atari without rules
#10Is there a way to learn Go from scratch using these AIs? I wonder if it would pay off in the long run to be fully trained by one.
You can play against open source reimplementations of some of the ideas behind AlphaGo family AIs. LeelaZero was one of the early ones, KataGo is probably your best bet right now. Sai is also in the mix.
All are _very_ strong. KataGo is ungodly strong, it beats pros.
Learning Go is about more than just playing against strong players, but it could help. The biggest difficulty is that the strong AIs aren't actually that good at playing handicap games, and they're also almost completely unable to explain to you why you should play one move over another.