Ariel Kwiatkowski

Comments

Ariel Kwiatkowski's Shortform

Looking for research idea feedback:

Learning to manipulate: consider a system with a large population of agents working on a certain goal, either learned or rule-based, but at this point - fixed. This could be an environment of ants using pheromones to collect food and bring it home.

Now add another agent (or some number of them) which learns in this environment, and tries to get other agents to instead fulfil a different goal. It could be ants redirecting others to a different "home", hijacking their work.


Does this sound interesting? If it works, would it potentially be publishable as a research paper? (or at least a post on LW) Any other feedback is welcome!

Draconarius's Shortform

But isn't the whole point that the hotel is full initially, and yet can accept more guests?

Ariel Kwiatkowski's Shortform

Has anyone tried to work with neural networks predicting the weights of other neural networks? I'm thinking about that in the context of something like subsystem alignment, e.g. in an RL setting where an agent first learns about the environment, and then creates the subagent (by outputting the weights or some embedding of its policy) who actually obtains some reward

Multi-agent safety

This reminds me of an idea bouncing around my mind recently, admittedly not aiming to solve this problem, but possibly exhibiting it.

Drawing inspiration from human evolution, then given a sufficiently rich environment where agents have some necessities for surviving (like gathering food), they could be pretrained with something like a survival prior which doesn't require any specific reward signals.

Then, agents produced this way could be fine-tuned for downstream tasks, or in a way obeying orders. The problem would arise when an agent is given an order that results in its death. We might want to ensure it follows its original (survival) instinct, unless overridden by a more specific order.

And going back to a multiagent scenario, similar issues might arise when the order would require antisocial behavior in a usually cooperative environment. The AI Economist comes to mind where that could come into play, where agents actually learn some nontrivial social relations https://blog.einstein.ai/the-ai-economist/