Vlad Mikulik

Karma: 910

Vlad Mikulik Dec 18, 2019, 11:07 PM
LW: 1 AF: 1
0
AF
in reply to: Matthew Barnett’s comment on: Is the term mesa optimizer too narrow?
I’m not talking about finding on optimiser-less definition of goal-directedness that would support the distinction. As you say, that is easy. I am interested in a term that would just point to the distinction without taking a view on the nature of the underlying goals.

As a side note I think the role of the intentional stance here is more subtle than I see it discussed. The nature of goals and motivation in an agent isn’t just a question of applying the intentional stance. We can study how goals and motivation work in the brain neuroscientifically (or at least, the processes in the brain that resemble the role played by goals in the intentional stance picture), and we experience goals and motivations directly in ourselves. So, there is more to the concepts than just taking an interpretative stance, though of course to the extent that the concepts (even when refined by neuroscience) are pieces of a model being used to understand the world, they will form part of an interpretative stance.

Vlad Mikulik Dec 18, 2019, 10:53 PM
LW: 1 AF: 1
0
AF
in reply to: Matthew Barnett’s comment on: Is the term mesa optimizer too narrow?
I understand that, and I agree with that general principle. My comment was intended to be about where to draw the line between incorrect theory, acceptable theory, and pre-theory.

In particular, I think that while optimisation is too much theory, goal-directedness talk is not, despite being more in theory-land than empirical malign generalisation talk. We should keep thinking of worries on the level of goals, even as we’re still figuring out how to characterise goals precisely. We should also be thinking of worries on the level of what we could observe empirically.

Vlad Mikulik Dec 18, 2019, 10:18 PM
LW: 6 AF: 4
0
AF
in reply to: Rohin Shah’s comment on: Is the term mesa optimizer too narrow?
We’re probably in agreement, but I’m not sure what exactly you mean by “retreat to malign generalisation”.

For me, mesa-optimisation’s primary claim isn’t (call it Optimisers) that agents are well-described as optimisers, which I’m happy to drop. It is the claim (call it Mesa≠Base) that whatever the right way to describe them is, in general their intrinsic goals are distinct from the reward.

That’s a specific (if informal) claim about a possible source of malign generalisation. Namely, that when intrinsic goals differ arbitrarily from the reward, then systems that competently pursue them may lead to outcomes that are arbitrarily bad according to the reward. Humans don’t pose a counterexample to that, and it seems prima facie conceptually clarifying, so I wouldn’t throw it away. I’m not sure if you propose to do that, but strictly, that’s what “retreating to malign generalisation” could mean, as malign generalisation itself makes no reference to goals.

One might argue that until we have a good model of goal-directedness, Mesa≠Base reifies goals more than is warranted, so we should drop it. But I don’t think so – so long as one accepts goals as meaningful at all, the underlying model need only admit a distinction between the goal of a system and the criterion according to which a system was selected. I find it hard to imagine a model or view that wouldn’t allow this – this makes sense even in the intentional stance, whose metaphysics for goals is pretty minimal.

It’s a shame that Mesa≠Base is so entangled with Optimisers. When I think of mesa-optimisation, I tend to think more about the former than about the latter. I wish there was a term that felt like it pointed directly to Mesa≠Base without pointing to Optimisers. The Inner Alignment Problem might be it, though it feels like it’s not quite specific enough.

Vlad Mikulik Dec 16, 2019, 1:00 PM
LW: 6 AF: 4
0
AF
on: Is the term mesa optimizer too narrow?
I’m sympathetic to what I see as the message of this post: that talk of mesa-optimisation is too specific given that the practical worry is something like malign generalisation. I agree that it makes extra assumptions on top of that basic worry, which we might not want to make. I would like to see more focus on inner alignment than on mesa-optimisation as such. I’d also like to see a broader view of possible causes for malign generalisation, which doesn’t stick so closely to the analysis in our paper. (In hindsight our analysis could also have benefitted from taking a broader view, but that wasn’t very visible at the time.)

At the same time, speaking only in terms of malign generalisation (and dropping the extra theoretical assumptions of a more specific framework) is too limiting. I suspect that solutions to inner alignment will come from taking an opinionated view on the structure of agents, clarifying its assumptions and concepts, explaining why it actually applies to real-world agents, and offering concrete ways in which the extra structure of the view can be exploited for alignment. I’m not sure that mesa-optimisation is the right view for that, but I do think that the right view will have something to do with goal-directedness.

Vlad Mikulik Sep 29, 2019, 12:13 AM
LW: 7 AF: 4
0
AF
in reply to: Rohin Shah’s comment on: A simple environment for showing mesa misalignment
By that I didn’t mean to imply that we care about mesa-optimisation in particular. I think that this demo working “as intended” is a good demo of an inner alignment failure, which is exciting enough as it is. I just also want to flag that the inner alignment failure doesn’t automatically provide an example of a mesa-optimiser.

Vlad Mikulik Sep 26, 2019, 9:57 AM
LW: 6 AF: 5
0
AF
on: A simple environment for showing mesa misalignment
I have now seen a few suggestions for environments that demonstrate misaligned mesa-optimisation, and this is one of the best so far. It combines being simple and extensible with being compelling as a demonstration of pseudo-alignment if it works (fails?) as predicted. I think that we will want to explore more sophisticated environments with more possible proxies later, but as a first working demo this seems very promising. Perhaps one could start even without the maze, just a gridworld with keys and boxes.

I don’t know whether observing key-collection behaviour here would be sufficient evidence to count for mesa-optimisation, if the agent has too simple a policy. There is room for philosophical disagreement there. Even with that, a working demo of this environment would in my opinion be a good thing, as we would have a concrete agent to disagree about.

Vlad Mikulik Sep 13, 2019, 9:55 AM
LW: 4 AF: 2
0
AF
in reply to: Wei Dai’s comment on: Utility ≠ Reward
Ah; this does seem to be an unfortunate confusion.

I didn’t intend to make ‘utility’ and ‘reward’ terminology – that’s what ‘mesa-‘ and ‘base’ objectives are for. I wasn’t aware of the terms being used in the technical sense as in your comment, so I wanted to use utility and reward as friendlier and familiar words for this intuition-building post. I am not currently inclined to rewrite the whole thing using different words because of this clash, but could add a footnote to clear this up. If the utility/reward distinction in your sense becomes accepted terminology, I’ll think about rewriting this.

That said, the distinctions we’re drawing appear to be similar. In your terminology, a utility-maximising agent is an agent which has an internal representation of a goal which it pursues. Whereas a reward-maximising agent does not have a rich internal goal representation but instead a kind of pointer to the external reward signal. To me this suggests your utility/reward tracks a very similar, if not the same, distinction between internal/external that I want to track, but with a difference in emphasis. When either of us says ‘utility ≠ reward’, I think we mean the same distinction, but what we want to draw from that distinction is different. Would you disagree?

Vlad Mikulik Sep 5, 2019, 11:14 PM
6 points
0
in reply to: Gordon Seidoh Worley’s comment on: Utility ≠ Reward
Thanks for raising this. While I basically agree with evhub on this, I think it is unfortunate that the linguistic justification is messed up as it is. I’ll try to amend the post to show a bit more sensitivity to the Greek not really working like intended.
Though I also think that “the opposite of meta”-optimiser is basically the right concept, I feel quite dissatisfied with the current terminology, with respect to both the “mesa” and the “optimiser” parts. This is despite us having spent a substantial amount of time and effort on trying to get the terminology right! My takeaway is that it’s just hard to pick terms that are both non-confusing and evocative, especially when naming abstract concepts. (And I don’t think we did that badly, all things considered.)
If you have ideas on how to improve the terms, I would like to hear them!

Vlad Mikulik Jun 24, 2019, 5:58 PM
LW: 10 AF: 6
0
AF
in reply to: Rohin Shah’s comment on: Risks from Learned Optimization: Introduction
You’re completely right; I don’t think we meant to have ‘more formally’ there.

Vlad Mikulik Jun 9, 2019, 6:53 PM
7 points
0
in reply to: Ofer’s comment on: Risks from Learned Optimization: Introduction
To some extent, but keep in mind that in another sense, the behavioural objective of maximising paperclips is totally consistent with playing along with the base objective for a while and then defecting. So I’m not sure the behaviour/mesa- distinction alone does the work you want it to do even in that case.

Vlad Mikulik Jun 9, 2019, 6:48 PM
LW: 4 AF: 3
0
AF
in reply to: tom4everitt’s comment on: Risks from Learned Optimization: Introduction
I’ve been meaning for a while to read Dennett with reference to this, and actually have a copy of Bacteria to Bach. Can you recommend some choice passages, or is it significantly better to read the entire book?

P.S. I am quite confused about DQN’s status here and don’t wish to suggest that I’m confident it’s an optimiser. Just to point out that it’s plausible we might want to call it one without calling PPO an optimiser.

P.P.S.: I forgot to mention in my previous comment that I enjoyed the objective graph stuff. I think there might be fruitful overlap between that work and the idea we’ve sketched out in our third post on a general way of understanding pseudo-alignment. Our objective graph framework is less developed than yours, so perhaps your machinery could be applied there to get a more precise analysis?

Vlad Mikulik Jun 8, 2019, 6:47 PM
LW: 15 AF: 7
0
AF
in reply to: tom4everitt’s comment on: Risks from Learned Optimization: Introduction
Thanks for an insightful comment. I think your points are good to bring up, and though I will offer a rebuttal I’m not convinced that I am correct about this.

What’s at stake here is: describing basically any system as an agent optimising some objective is going to be a leaky abstraction. The question is, how do we define the conditions of calling something an agent with an objective in such a way to minimise the leaks?

Distinguishing the “this system looks like it optimises for X” from “this system internally uses an evaluation of X to make decisions” is useful from the point of view of making the abstraction more robust. The former doesn’t make clear what makes the abstraction “work”, and so when to expect it to fail. The latter will at least tell you what kind of failures to expect in the abstraction: places where the evaluation of X doesn’t connect to the rest of the system like it’s supposed to. In particular, you’re right that if the learned environment model doesn’t generalise, the mesa-objective won’t be predictive of behaviour. But that’s actually a prediction of taking this view. On the other hand, it is unclear if taking the behavioural view would predict that the system will change its behaviour off-distribution (partially, because it’s unclear what exactly grounds the similarities in behaviour on-distribution).

I think it definitely is useful to also think about the behavioural objective in the way you describe, because the later concerns we raise basically do also translate to coherent behavioural objectives. And I welcome more work trying to untangle these concepts from one another, or trying to dissolve any of them as unnecessary. I am just wary of throwing away seemingly relevant assumptions about internal structure before we can show they’re unhelpful.

Re: DQN

You’re also right to point out DQN as an interesting edge case. But I am actually unsure that DQN agents should be considered non-optimisers, in the sense that they do perform rudimentary optimisation: they take an argmax of the Q function. The Q function is regressed to the episode returns. If the learning goes well, the Q function is literally representing the agent’s objective (indeed, it’s not really selected to maximise return; its selected to be accurate at predicting return). Contrast this with e.g. policy optimisation trained agents, which are not supposed to directly represent an objective, but are supposed to score well on it. (Someone good at running RL experiments maybe should look into comparing the coherence of revealed preferences of DQN agents with PPO agents. I’d read that paper.)

Vlad Mikulik Jun 8, 2019, 6:15 PM
LW: 10 AF: 4
0
AF
in reply to: Richard_Ngo’s comment on: Risks from Learned Optimization: Introduction
I think humans are fairly weird because we were selected for an objective that is unlikely to be what we select for in our AIs.

That said, if we model AI success as driven by model size and compute (with maybe innovations in low-level architecture), then I think that the way humans represent objectives is probably fairly close to what we ought to expect.

If we model AI success as mainly innovative high-level architecture, then I think we will see more explicitly represented objectives.

My tentative sense is that for AI to be interpretable (and safer) we want it to be the latter kind, but given enough compute the former kind of AI will give better results, other things being equal.

Here, what I mean by low-level architecture is something like “we’ll use lots of LSTMs instead of lots of plain RNNs, but keep the model structure simple: plug in the inputs, pass it through some layers, and read out the action probabilities”, and high-level is something like “let’s organise the model using this enormous flowchart with all of these various pieces that each are designed to take a particular role; here’s the observation embedding, here’s the search in latent model space, here’s the …”

Vlad Mikulik Jun 6, 2019, 7:10 AM
LW: 4 AF: 3
0
AF
in reply to: Rohin Shah’s comment on: Conditions for Mesa-Optimization
Yes, it probably doesn’t apply to most objectives. Though it seems to me that the closer the task is to something distinctly human, the more probable it is that this kind of consideration can apply. E.g., making judgements in criminal court cases and writing fiction are domains where it’s not implausible to me that this could apply.

I do think this is a pretty speculative argument, even for this sequence.

Vlad Mikulik Jun 4, 2019, 10:51 AM
LW: 4 AF: 3
0
AF
in reply to: Rohin Shah’s comment on: Conditions for Mesa-Optimization
The main benefit I see of hardcoding optimisation is that, assuming the system’s pieces learn as intended (without any mesa-optimisation happening in addition to the hardcoded optimisation) you get more access and control as a programmer over what the learned objective actually is. You could attempt to regress the learned objective directly to a goal you want, or attempt to enforce a certain form on it, etc. When the optimisation itself is learned*, the optimiser is more opaque, and you have fewer ways to affect what goal is learned: which weights of your enormous LSTM-based mesa-optimiser represent the objective?
This doesn’t solve the problem completely (you might still learn an objective that is very incorrect off-distribution, etc.), but could offer more control and insight into the system to the programmer.
*Of course, you can have learned optimisation where you keep track of the objective which is being optimised (like in Learning to Learn by Gradient Descent), but I’d class that more under hard-coded optimisation for the purposes of this discussion. Here I mean the kind of learned optimisation that happens where you’re not building the architecture explicitly around optimising or learning to optimise.

Vlad Mikulik Jun 4, 2019, 10:41 AM
LW: 4 AF: 3
0
AF
in reply to: Rohin Shah’s comment on: Conditions for Mesa-Optimization
The section on human modelling annoyingly conflates two senses of human modelling. One is the sense you talk about, the other is seen in the example:
For example, it might be the case that predicting human behavior requires instantiating a process similar to human judgment, complete with internal motives for making one decision over another.
The idea there isn’t that the algorithm simulates human judgement as an external source of information for itself, but that the actual algorithm learns to be a human-like reasoner, with human-like goals (because that’s a good way of approximating the output of human-like reasoning). In that case, the agent really is a mesa-optimiser, to the degree that a goal-directed human-like reasoner is an optimiser.
(I’m not sure to what degree it’s actually likely that a good way to approximate the behaviour of human-like reasoning is to instantiate human-like reasoning)

Vlad Mikulik Jun 2, 2019, 8:03 PM
LW: 12 AF: 7
0
AF
in reply to: abramdemski’s comment on: Selection vs Control

to what extent are mesa-controllers with simple behavioural objectives going to be simple?

I’m not sure what “simple behavioural objective” really means. But I’d expect that for tasks requiring very simple policies, controllers would do, whereas the more complicated the policy required to solve a task, the more one would need to do some kind of search. Is this what we observe? I’m not sure. AlphaStar and OpenAI Five seem to do well enough in relatively complex domains without any explicit search built into the architecture. Are they using their recurrence to search internally? Who knows. I doubt it, but it’s not implausible.

certain kinds of mesa-controllers can be simple: the mesa-controllers which are more like my rocket example (explicit world-model; explicit representation of objective within that world model; but, optimal policy does not use any search).

The rocket example is interesting. I guess the question for me there is, what sorts of tasks admit an optimal policy that can be represented in this way? Here it also seems to me like the more complex an environment, the more implausible it seems that a powerful policy can be successfully represented with straightforward functions. E.g., let’s say we want a rocket not just to get to the target, but to self-identify a good target in an area and pick a trajectory that evades countermeasures. I would be somewhat surprised if we can still represent the best policy as a set of non-searchy functions. So I have this intuition that for complex state spaces, it’s hard to find pure controllers that do the job well.

Vlad Mikulik Jun 2, 2019, 3:38 PM
LW: 20 AF: 12
0
AF
on: Selection vs Control
(I am unfortunately currently bogged down with external academic pressures, and so cannot engage with this at the depth I’d like to, but here’s some initial thoughts.)

I endorse this post. The distinction explained here seems interesting and fruitful.

I agree with the idea to treat selection and control as two kinds of analysis, rather than as two kinds of object – I think this loosely maps onto the distinction we make between the mesa-objective and the behavioural objective. The former takes the selection view of the learned algorithm; the latter takes the control view.

At least speaking for myself (the other authors might have different thoughts on this), the decision to talk explicitly in terms of the selection view in the mesa-optimiser post is based on an intuition that selectors, in general, have more coherently defined counterfactual behaviour. That is, given a very different input, a selector will still select an output that scores well on its mesa-objective, because that’s how selectors work. Whereas a controller, to the degree it optimises for an objective, seems more likely to just completely stop working on a different input. I have fairly low confidence in this argument, however: it seems to me that one can plausibly have pretty coherent counterfactual behaviour in a very broad distribution even without doing selection. And since it is ultimately the behaviour that does the damage, it would be good to have a working distinction that is based purely on that. We (the mesa-optimisation authors) haven’t been able to come up with one.

Another reason to be interested in selectors is that in RL, the learned algorithm is supposed to fill a controller role. So, restricting attention to selectors allows to talk at least somewhat meaningfully about non-optimiser agents, which is otherwise difficult, as any learned agent is in a controller-shaped context.

In any case, I hope that more work happens on this problem, either dissolving the need to talk about optimisation, or at least making all these distinctions more precise. The vagueness of everything is currently my biggest worry about the legitimacy of mesa-optimiser concerns.

Vlad Mikulik Mar 27, 2019, 12:22 AM
LW: 3 AF: 2
0
AF
in reply to: TurnTrout’s comment on: More realistic tales of doom
The goal that the agent is selected to score well on is not necessarily the goal that the agent is itself pursuing. So, unless the agent’s internal goal matches the goal for which it’s selected, the agent might still seek influence because its internal goal permits that. I think this is in part what Paul means by “Avoiding end-to-end optimization may help prevent the emergence of influence-seeking behaviors (by improving human understanding of and hence control over the kind of reasoning that emerges)”

Vlad Mikulik Jul 17, 2018, 5:27 AM
2 points
0
on: Probabilistic decision-making as an anxiety-reduction technique
I also use a simple version of this, with a key extra step at the end:

1) have a decision you are unsure about. 2) perform randomisation (I usually just use a coin). 3) notice how the outcome makes you feel. If you find that you wish the coin landed the other way, override the decision and do what you secretly wanted to do all along.

You might think the third step defeats the purpose of the exercise, but so long as you actually commit to following the randomisation most of the time, it gives you direct access to very useful information. It also sets up the right incentive, wherein you never really need to work your willpower against your desires (except, I guess, the desire to deliberate more).

I mostly use this for a slightly different use case – inconsequential decisions like where to eat or small purchases, where taking a lot of time to optimise isn’t worth it. Your mileage may vary with more important decisions, but I see no reason in principle this couldn’t work.