Director of AI research at ALTER, where I lead a group working on the learning-theoretic agenda for AI alignment. I'm also supported by the LTFF. See also LinkedIn.
E-mail: {first name}@alter.org.il
This post is a collection of claims about acausal trade, some of which I find more compelling and some less. Overall, I think it's a good contribution to the discussion.
Claims that I mostly agree with include:
Claims that I have some quibbles with include:
This post argues that, while it's traditional to call policies trained by RL "agents", there is no good reason for it and the terminology does more harm than good. IMO Turner has a valid point, but he takes it too far.
What is an "agent"? Unfortunately, this question is not discussed in the OP in any detail. There are two closely related informal approaches to defining "agents" that I like, one more axiomatic / black-boxy and the other more algorithmic / white-boxy.
The algorithmic definition is: An agent is a system that can (i) learn models of its environment (ii) use learned models to generate plans towards a particular goal (iii) execute these plans.
Under this definition, is an RL policy an "agent"? Not necessarily. There is a much stronger case for arguing that the RL algorithm, including the training procedure, is an agent. Indeed, such an algorithm (i) learns a model of the environment (at least if it's model-based RL: if it's model-free it might still do so implicitly, but it's less clear) (ii) generates a plan (the policy) (iii) executes the plans (when the policy is executed, i.e. in inference/deployment time). Whether the policy in itself is an agent amounts to asking whether the policy is capable of in-context RL (which is far from obvious). Moreover, the case for calling the system an agent is stronger when it learns online and weaker (but not completely gone) when there is a separation into non-overlapping training and deployment phases, as often done in contemporary systems.
The axiomatic definition is: An agent is a system that effectively pursues a particular goal in an unknown environment. That is, it needs to perform well (as measured by achieving the goal) when placed in a large variety of different environments.
With this definition we reach similar conclusions. An online RL system would arguably adapt to its environment and optimize towards achieving the goal (which is maximizing the reward). A trained policy will not necessarily do it: if it was trained in a particular environment, it can become completely ineffective in other environments!
Importantly, even an online RL system can easily fail at agentic-ness, depending how good its learning algorithm is for dealing with distributional shift, nonrealizability etc. Nevertheless, the relation between agency and RL is pretty direct, more so than the OP implies.
This post proposes an approach to decision theory in which we notion of "actions" is emergent. Instead of having an ontologically fundamental notion of actions, the agent just has beliefs, and some of them are self-fulfilling prophecies. For example, the agent can discover that "whenever I believe my arm will move up/down, my arm truly moves up/down", and then exploit this fact by moving the arm in the right direction to maximize utility. This works by having a "metabelief" (a mapping from beliefs to beliefs; my terminology, not the OP's) and allowing the agent to choose its belief out of the metabelief fixed points.
The next natural question is then, can we indeed demonstrate that an agent will learn which part of the world it controls, under reasonable conditions. Abram implies that it should be possible if we only allow choice among attractive fixed point. He then bemoans the need for this restriction and tries to use ideas from Active Inference to fix it with limited success. Personally, I don't understand what's so bad with staying with the attractive fixed points.
Unfortunately, this post avoids spelling out a sequential version of the decision theory, which would be necessary to actually establish any learning-theoretic result. However, I think that I see how it can be done, and it seems to support Abram's claims. Details follows.
Let's suppose that the agent observes two systems, each of which can be in one of two positions. At each moment of time, it observes an element of , where . The agent beliefs it can control one of and whereas the other is a fair coin. However, it doesn't know which is which.
In this case, metabeliefs are mappings of type . Specifically, we have a hypothesis that asserts is controllable, a hypothesis that asserts is controllable and the overall metabelief is (say) .
The hypothesis is defined by
Here, , , , and is some "motor response function", e.g. .
Similarly, is defined by
Now, let be an attractive fixed point of and consider some history . If the statistics of in seem biased towards whereas the statistics of in seem like a fair coin, then the likelihoods will satisfy and hence will be close to and therefore will be close to (since is an attractive fixed point). On the other hand, in the converse situation, the likelihoods will satisfy and hence will be close to . Hence, the agent effectively updates on the observed history and will choose some fixed point which controls the available degrees of freedom correctly.
Notice that all of this doesn't work with repelling fixed points. Indeed, if we used then would have a unique fixed point and there would be nothing to choose.
I find these ideas quite intriguing and am likely to keep thing about them!
I feel that coherence arguments, broadly construed, are a reason to be skeptical of such proposals, but debating coherence arguments because of this seems backward. Instead, we should just be discussing your proposal directly. Since I haven't read your proposal yet, I don't have an opinion, but some coherence-inspired question I would be asking are:
This post tries to push back against the role of expected utility theory in AI safety by arguing against various ways to derive expected utility axiomatically. I heard many such arguments before, and IMO they are never especially useful. This post is no exception.
The OP presents the position it argues against as follows (in my paraphrasing): "Sufficiently advanced agents don't play dominated strategies, therefore, because of [theorem], they have to be expected utility maximizers, therefore they have to be goal-directed and [other conclusions]". They then proceed to argue that there is no theorem that can make this argument go through.
I think that this entire framing is attacking a weak man. The real argument for expected utility theory is:
In conclusion, there are coherence theorems. But, more important than individual theorems are the "coherence theories".
I kinda agree with the claim, but disagree with its framing. You're imagining that peer pressure is something extraneous to the person's core personality, which they want to resist but usually fail. Instead, the desire to fit in, to be respected, liked and admired by other people, is one of the core desires that most (virtually all?) people have. It's approximately on the same level as e.g. the desire to avoid pain. So, people don't "succumb to peer pressure", they (unconsciously) choose to prioritize social needs over other considerations.
At the same time, the moral denouncing of groupthink is mostly a self-deception defense against hostile telepaths. With two important caveats:
This remains the best overview of the learning-theoretic agenda to-date. As a complementary pedagogic resource, there is now also a series of video lectures.
Since the article was written, there were several new publications:
In addition, some new developments were briefly summarized in short-forms:
Meanwhile, active research proceeds along several parallel directions:
It remains true that there are more shovel-ready open problems than researchers, and hence the number of (competent) researchers is still the bottleneck.
Seems right, but is there a categorical derivation of the Wentworth-Lorell rules? Maybe they can be represented as theorems of the form: given an arbitrary Markov category C, such-and-such identities between string diagrams in C imply (more) identities between string diagrams in C.
This post introduces Timaeus' "Developmental Interpretability" research agenda. The latter is IMO one of the most interesting extant AI alignment research agendas.
The reason DevInterp is interesting is that it is one of the few AI alignment research agendas that is trying to understand deep learning "head on", while wielding a powerful mathematical tool that seems potentially suitable for the purpose (namely, Singular Learning Theory). Relatedly, it is one of the few agendas that maintains a strong balance of theoretical and empirical research. As such, it might also grow to be a bridge between theoretical and empirical research agendas more broadly (e.g. it might be synergistic with the LTA).
I also want to point out a few potential weaknesses or (minor) reservations I have:
First, DevInterp places phase transitions as its central object of study. While I agree that phase transitions seem interesting, possibly crucial to understand, I'm not convinced that a broader view wouldn't be better.
Singular Learning Theory (SLT) has the potential to explain generalization in deep learning, phase transitions or no. This in itself seems to be important enough to deserve the central stage. Understanding generalization is crucial, because:
Hence, compared to the OP, I would put more emphasis on these latter points.
Second, the OP does mention the difference between phase transitions during Stochastic Gradient Descent (SGD) and the phase transitions of Singular Learning Theory, but this deserves a closer look. SLT has IMO two key missing pieces:
That said, if the above missing pieces were found, SLT would become straightforwardly the theory for understanding deep learning and maybe learning in general.