there are policies which are successful because they describe a particular strategy to follow (non-mesaoptimizers), and policies that contain some strategy for discovering more strategies (mesaoptimizers). a way to view the relation this has to speed/complexity priors that doesn’t depend on search in particular is that policies that work by discovering strategies tend to be simpler and more generic (they bake in very little domain knowledge/metis, and are applicable to a broader set of situations because they work by coming up with a strategy for the task at hand on the fly). in contrast, policies that work by knowing a specific strategy tend to be more complex because they have to bake in a ton of domain knowledge, are less generally useful because they specifically know what to do in that situation, and thereby are also less retargetable)
another observation is that a meta-strategy with the ability to figure out what strategy is good is kind of defined by the fact that it doesn’t bake in specifics of dealing with a particular situation, but rather can adapt to a broad set of situations. there are also different degrees of meta-strategy-ness; some meta strategies will more quickly adapt to a broader set of situations. (there’s probably some sort of NFLT kind of argument you can make but NFLTs in general don’t really matter)
there are policies which are successful because they describe a particular strategy to follow (non-mesaoptimizers), and policies that contain some strategy for discovering more strategies (mesaoptimizers). a way to view the relation this has to speed/complexity priors that doesn’t depend on search in particular is that policies that work by discovering strategies tend to be simpler and more generic (they bake in very little domain knowledge/metis, and are applicable to a broader set of situations because they work by coming up with a strategy for the task at hand on the fly). in contrast, policies that work by knowing a specific strategy tend to be more complex because they have to bake in a ton of domain knowledge, are less generally useful because they specifically know what to do in that situation, and thereby are also less retargetable)
another observation is that a meta-strategy with the ability to figure out what strategy is good is kind of defined by the fact that it doesn’t bake in specifics of dealing with a particular situation, but rather can adapt to a broad set of situations. there are also different degrees of meta-strategy-ness; some meta strategies will more quickly adapt to a broader set of situations. (there’s probably some sort of NFLT kind of argument you can make but NFLTs in general don’t really matter)
the ability to figure out strategies doesn’t necessarily have to be all reasoning, it can also encompass the experimental skillset