AI ALIGNMENT FORUM
AF

All of AdamGleave's Comments + Replies

I googled "model-based RL Atari" and the first hit was this which likewise tries to learn the reward function by supervised learning from observations of past rewards (if I understand correctly)

Ah, the "model-based using a model-free RL algorithm" approach :) They learn a world model using supervised learning, and then use PPO (a model-free RL algorithm) to train a policy in it. It sounds odd but it makes sense: you hopefully get much of the sample efficiency of model-based training, while still retaining the state-of-the-art results of model-free RL. You'... (read more)

Inner Alignment in Salt-Starved Rats

AdamGleave6mo2

Thanks for the clarification! I agree if the planner does not have access to the reward function then it will not be able to solve it. Though, as you say, it could explore more given the uncertainty.

Most model-based RL algorithms I've seen assume they can evaluate the reward functions in arbitrary states. Moreover, it seems to me like this is the key thing that lets rats solve the problem. I don't see how you solve this problem in general in a sample-efficient manner otherwise.

One class of model-based RL approaches is based on [model-predictive control](ht... (read more)

1Steve Byrnes6moHmm. AlphaZero can evaluate the true reward function in arbitrary states. MuZero can't—it tries to learn the reward function by supervised learning from observations of past rewards (if I understand correctly). I googled "model-based RL Atari" and the first hit was this [https://arxiv.org/abs/1903.00374] which likewise tries to learn the reward function by supervised learning from observations of past rewards (if I understand correctly). I'm not intimately familiar with the deep RL literature, I wouldn't know what's typical and I'll take your word for it, but it does seem that both possibilities are out there. Anyway, I don't think the neocortex can evaluate the true reward function in arbitrary states, because it's not a neat mathematical function, it involves messy things like the outputs of millions of pain receptors, hormones sloshing around, the input-output relationships of entire brain subsystems containing tens of millions of neurons, etc. So I presume that the neocortex tries to learn the reward function by supervised learning from observations of past rewards—and that's the whole thing with TD learning and dopamine. I added a new sub-bullet at the top to clarify that it's hard to explain by RL unless you assume the planner can query the ground-truth reward function in arbitrary hypothetical states. And then I also added a new paragraph to the "other possible explanations" section at the bottom saying what I said in the paragraph just above. Thank you. Well, the rats are trying to do the rewarding thing after zero samples, so I don't think "sample-efficiency" is quite the right framing. In ML today, the reward function is typically a function of states and actions, not "thoughts". In a brain, the reward can depend directly on what you're imagining doing or planning to do, or even just what you're thinking about. That's my proposal here. Well, I guess you could say that this is still a "normal MDP", but where "having thoughts" and "having ideas" etc. a

Inner Alignment in Salt-Starved Rats

AdamGleave6mo8

I'm a bit confused by the intro saying that RL can't do this, especially since you later on say the neocortex is doing model-based RL. I think current model-based RL algorithms would likely do fine on a toy version of this task, with e.g. a 2D binary state space (salt deprived or not; salt water or not) and two actions (press lever or no-op). The idea would be:

- Agent explores by pressing lever, learns transition dynamics that pressing lever => spray of salt water.

- Planner concludes that any sequence of actions involving pressing lever wi... (read more)

3Steve Byrnes6moGood question! Sorry I didn't really explain. The missing piece is "the planner will conclude this has positive reward". The planner has no basis for coming up with this conclusion, that I can see. In typical RL as I understand it, regardless of whether it's model-based or model-free, you learn about what is rewarding by seeing the outputs of the reward function. Like, if an RL agent is playing an Atari game, it does not see the source code that calculates the reward function. It can try to figure out how the reward function works, for sure, but when it does that, all it has to go on is the observations of what the reward function has output in the past. ( Related discussion [https://www.lesswrong.com/posts/Ca3sCRGfWvXvYC5YC/what-are-some-non-purely-sampling-ways-to-do-deep-rl] .) So yeah, in the salt-deprived state, the reward function has changed. But how does the planner know that? It hasn't seen the salt-deprived state before. Presumably if you built such a planner, it would go in with a default assumption of "the salt-deprivation state is different now than I've ever seen before—I'll just assume that that doesn't affect the reward function!" Or at best, its default assumption would be "the salt deprivation state is different now than I've ever seen before—I don't know how and whether that impacts the reward function. I should increase my uncertainty. Maybe explore more.". In this experiment the rats were neither of those, instead they were acting like "the salt deprivation state is different than I've ever seen, and I specifically know that, in this new state, very salty things are now very rewarding". They were not behaving as if they were newly uncertain about the reward consequences of the lever, they were absolutely gung-ho about pressing it. Sorry if I'm misunderstanding :-)

The ground of optimization

AdamGleave10mo7

Thanks for the post, this is my favourite formalisation of optimisation so far!

One concern I haven't seen raised so far, is that the definition seems very sensitive to the choice of configuration space. As an extreme example, for any given system, I can always augment the configuration space with an arbitrary number of dummy dimensions, and choose the dynamics such that these dummy dimensions always get set to all zero after each time step. Now, I can make the basin of attraction arbitrarily large, while the target configuration set remains a fixed si... (read more)

Following human norms

AdamGleave2y5

I feel like there are three facets to "norms" v.s. values, which are bundled together in this post but which could in principle be decoupled. The first is representing what not to do versus what to do. This is reminiscent of the distinction between positive and negative rights, and indeed most societal norms (e.g. human rights) are negative, but not all (e.g. helping an injured person in the street is a positive right). If the goal is to prevent catastrophe, learning the 'negative' rights is probably more important, but it seems to me t... (read more)

1Rohin Shah2yYeah, agreed with all of that, thanks for the comment. You could definitely try to figure out each of these things individually, eg. learning constraints that can be used with Constrained Policy Optimization [https://arxiv.org/abs/1705.10528] is along the "what not to do" axis, and a lot of the multiagent RL work is looking at how we can get some norms to show up with decentralized training. But I feel a lot more optimistic about research that is trying to do all three things at once, because I think the three aspects do interact with each other. At least, the first two feel very tightly linked, though they probably can be separated from the multiagent setting.