Our team in SERI MATS needs to choose a project to work on for the next month. We spent the first two weeks discussing the alignment problem and what makes it difficult, and proposing (lots of) projects to look for one that we think would directly address the hard parts of the alignment problem.
We're writing this post to get feedback and criticism of this project proposal. Please let us know if you think this is a suboptimal project in any way.
Disclaimer: We've probably misunderstood some things, don't assume anything in this post accurately represents Vanessa's ideas.
Our project is motivated by Vanessa Kosoy’s PreDCA proposal. We want to understand this proposal in enough detail that we can simplify it, as well as see and patch any holes.
IBP gives us several key tools:
Together these tools could give a solution to the pointers problem, which we believe is a core problem in alignment. We will start this by understanding and testing Vanessa’s definition of agency.
The following is Vanessa's definition of the intelligence of an agent, where an agent is a program, denoted by G, that outputs policies (as described in Evaluating Agents in IBP). This can be used to identify agents in a world model.
Definition 1.6: Denote G∗:H→A the policy actually implemented by G. Fix ξ∈Δ(AH). The physicalist intelligence of G relative to the baseline policy mixture ξ, prior ζ and loss function L is defined by:
In words, this says that the intelligence of the agent G, given a loss function L, is the negative log of the probability that a random policy π is better than the actual policy the agent implements, denoted by G∗.
The next part is how to extract (a distribution over) the utility function of a given agent (from video on PreDCA):
Here, Lpol is just the negative of the utility function U. Combining this with the definition of intelligence above gives a simpler representation:
In words, the probability that agent G has utility function U is exponentially increasing in the intelligence of G implied by U and exponentially decreasing in the Kolmorogov complexity of U.
In order to do this properly, we will need to understand and distill large sections of Infra-Bayesian Physicalism. Part of the project will be publishing our understanding, and we hope that other people looking to understand and build on IBP will benefit from this distillation.
That's where we are right now -- let us know what you think!
"Agentometer" and "Utiliscope" are not Vanessa's terminology.
In keeping with the tradition of InfraBayes, I do not understand what you actually plan to test. But "empirically test IBP" sure does sound like a great project!
The way we see this project going concretely looks something like:
First things first, we want to get a good enough theoretical background of IBP. This will ultimately result in something like a distillation of IBP that we will use as reference, and hope others will get a lot of use from.
In this process, we will be doing most of our testing in a theoretical framework. That is to say, we will be constructing model agents and seeing how InfraBayesian Physicalism actually deals with these in theory, whether it breaks down at any stage (as judged by us), and if so whether we can fix or avoid those problems somehow.
What comes after this, as we see it at the moment, is trying to implement the principles of InfraBayesian Physicalism in a real-life, honest-to-god, Inverse Reinforcment Learning proposal. We think IBP stands a good chance of being able to patch some of the largest problems in IRL, which should ultimately be demonstrable by actually making an IRL proposal that works robustly. (When this inevitably fails the first few times, we will probably return to step 1, having gained useful insights, and iterate).
I'm glad that you guys are interested in working on IBP/PreDCA. Here are a few points that might help you:
Also, I am completely open to discussing the details of your project in private, if you're serious about it.
Thank you so much for your thoughtful reply. To respond to a few of your points:
We would very much appreciate discussing details in private, we are serious about it. I'll follow up with a DM on LessWrong soon.