Vanessa Kosoy's Shortform

Vanessa Kosoy

This is a special post for quick takes by Vanessa Kosoy. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

One of the central challenges in Dialogic Reinforcement Learning is dealing with fickle users, i.e. the user changing eir mind in illegible ways that cannot necessarily be modeled as, say, Bayesian updating. To take this into account, we cannot use the naive notion of subjective regret bound, since the user doesn't have a well-defined prior. I propose to solve this by extending the notion of dynamically inconsistent preferences to dynamically inconsistent beliefs. We think of the system as a game, where every action-observation history $h \in {(A \times O)}^{*}$ corresponds to its own player. The action space of each player is just $A$ . An outcome of such a game can be also thought of as a policy $π$ for the AI. The payoff of a player is expected utility (for this player's reward function) w.r.t. the probability measure resulting from $π$ plus the current belief state of the user conditional on $h$ , $μ ∣ h \in Δ R$ ( $R$ is the set of possible "realities"). We then define regret as the sum of Bellman errors w.r.t. equilibrium value of the players that actually manifested (so that in equilibrium it is zero). Bayesian regret requires taking expected value w.r.t some "ur-prior" that the AI starts with. Note that:

For a user that updates its beliefs on the AI's observations according the Bayes' theorem, the regret per reality is the same as subjective regret. Bayesian regret is also the same if the ur-prior assumes the user's beliefs are calibrated (which in the more general case is not a necessary assumption). The same applies to a user that doesn't updates eir beliefs at all.
The user beliefs are part of the ontology $R$ . Therefore, the system takes into accounts the user's beliefs about the evolution of the user's beliefs. So, the equilibrium policy is incentivized to empower its future self to the extent that the user believes that eir own beliefs will become more accurate over time (given fixed reward function, see below).
$R$ contains a distinct reward function for each player. And, the user may have uncertainty even over eir own current reward function. Therefore, the system distinguishes two types of value modifications: "legitimate" modifications that consist of improving one's beliefs about the reward function and "illegitimate" modification that consist of the reward function actually changing. The equilibrium policy is incentivized to encourage the first type and avoid the second type.

1Vanessa Kosoy7y

There is a deficiency in this "dynamically subjective" regret bound (also can be called "realizable misalignment" bound) as a candidate formalization of alignment. It is not robust to scaling down. If the AI's prior allows it to accurately model the user's beliefs (realizability assumption), then the criterion seems correct. But, imagine that the user's beliefs are too complex and an accurate model is not possible. Then the realizability assumption is violated and the regret bound guarantees nothing. More precisely, the AI may use incomplete models to capture some properties of the user's beliefs and exploit them, but this might be not good enough. Therefore, such an AI might fall into a dangerous zone when it is powerful enough to cause catastrophic damage but not powerful enough to know it shouldn't do it. To fix this problem, we need to introduce another criterion which has to hold simultaneously with the misalignment bound. We need that for any reality that satisfies the basic assumptions built into the prior (such as, the baseline policy is fairly safe, most questions are fairly safe, human beliefs don't change too fast etc), the agent will not fail catastrophically. (It would be way too much to ask it would converge to optimality, it would violate no-free-lunch.) In order to formalize "not fail catastrophically" I propose the following definition. Let's start with the case when the user's preferences and beliefs are dynamically consistent. Consider some AI-observable event S that might happen in the world. Consider a candidate learning algorithm πlearn and two auxiliary policies. The policy πbase→S follows the baseline policy until S happens, at which time it switches to the subjectively optimal policy. The policy πlearn→S follows the candidate learning algorithm until S happens, at which time it also switches to the subjectively optimal policy. Then, the "S-dangerousness" of πlearn is defined to be the expected utility of πbase→S minus the expected utility

1TurnTrout7y

This seems quite close (or even identical) to attainable utility preservation; if I understand correctly, this echoes arguments I've made for why AUP has a good shot of avoiding catastrophes and thereby getting you something which feels similar to corrigibility.

There is some similarity, but there are also major differences. They don't even have the same type signature. The dangerousness bound is a desideratum that any given algorithm can either satisfy or not. On the other hand, AUP is a specific heuristic how to tweak Q-learning. I guess you can consider some kind of regret bound w.r.t. the AUP reward function, but they will still be very different conditions.

The reason I pointed out the relation to corrigibility is not because I think that's the main justification for the dangerousness bound. The motivation for... (read more)

Vanessa Kosoy's Shortform

6

Vanessa Kosoy's Shortform

6