Now, this does all fit into the broader pattern of “leveraging computation”. Fair enough, I guess, but what else would you expect?
It also fits into the pattern of (as you yourself pointed out) minimizing human knowledge during the construction of these programs, allowing them to tease out the features of the problem space on their own. The claim here is that as computing power increases, domain-agnostic approaches (i.e. approaches that do not require programmers to explicitly encode human-created heuristics) will increasingly outperform domain-specific approaches (which do rely on externally encoded human knowledge).
This is a non-trivial claim! For example, it wasn’t at all obvious prior to January 2017 that traditional chess engines (whose static evaluation functions are filled with human-programmed heuristics) could be overtaken by a pure learning-based approach, and yet the AlphaZero paper came out and showed it was possible. If the larger claim is true, then that might suggest directions for further research—in particular, approaches that abstract away large parts of a problem may have more success than approaches that focus on the details of the problem structure.
Yes, that’s fair. (Though I’m not sure about the terms “domain-agnostic” and “domain-specific”; e.g., the AlphaZero approach seems to work well for a wide variety of board games played on “regular” boards but would need substantial modification to apply even to other board games and isn’t obviously applicable at all to anything that isn’t more or less a board game.)
It also fits into the pattern of (as you yourself pointed out) minimizing human knowledge during the construction of these programs, allowing them to tease out the features of the problem space on their own. The claim here is that as computing power increases, domain-agnostic approaches (i.e. approaches that do not require programmers to explicitly encode human-created heuristics) will increasingly outperform domain-specific approaches (which do rely on externally encoded human knowledge).
This is a non-trivial claim! For example, it wasn’t at all obvious prior to January 2017 that traditional chess engines (whose static evaluation functions are filled with human-programmed heuristics) could be overtaken by a pure learning-based approach, and yet the AlphaZero paper came out and showed it was possible. If the larger claim is true, then that might suggest directions for further research—in particular, approaches that abstract away large parts of a problem may have more success than approaches that focus on the details of the problem structure.
Yes, that’s fair. (Though I’m not sure about the terms “domain-agnostic” and “domain-specific”; e.g., the AlphaZero approach seems to work well for a wide variety of board games played on “regular” boards but would need substantial modification to apply even to other board games and isn’t obviously applicable at all to anything that isn’t more or less a board game.)
And MuZero, which applies to ALE very well?
MuZero seems to deserve to be called domain-agnostic more than AlphaZero does, yes.
(For anyone else who doesn’t immediately recognize the abbreviation: ALE is the “Arcade Learning Environment”.)