Intelligent Agent Foundations Forumsign up / log in
Indifference and compensatory rewards
discussion post by Stuart Armstrong 432 days ago | discuss

A putative new idea for AI control; index here.

It’s occurred to me that there is a framework where we can see all “indifference” results as corrective rewards, both for the utility function change indifference and for the policy change indifference.

Imagine that the agent has reward \(R_0\) and is following policy \(\pi_0\), and we want to change it to having reward \(R_1\) and following policy \(\pi_1\).

Then the corrective reward we need to pay it, so that it doesn’t attempt to resist or cause that change, is simply the difference between the two expected values:

  • \(V(R_0|\pi_0)-V(R_1|\pi_1)\),

where \(V\) is the agent’s own valuation of the expected reward, conditional on the policy.

This explains why off-policy reward-based agents are already safely interruptible: since we change the policy, not the reward, \(R_0=R_1\). And since off-policy agents have value estimates that are indifferent to the policy followed, \(V(R_0|\pi_0)=V(R_1|\pi_1)\), and the compensatory rewards are zero.





I think that in that case,
by Alex Appel on Smoking Lesion Steelman | 1 like

Two minor comments. First,
by Sam Eisenstat on No Constant Distribution Can be a Logical Inductor | 1 like

A: While that is a really
by Alex Appel on Musings on Exploration | 0 likes

> The true reason to do
by Jessica Taylor on Musings on Exploration | 0 likes

A few comments. Traps are
by Vadim Kosoy on Musings on Exploration | 1 like

I'm not convinced exploration
by Abram Demski on Musings on Exploration | 0 likes

Update: This isn't really an
by Alex Appel on A Difficulty With Density-Zero Exploration | 0 likes

If you drop the
by Alex Appel on Distributed Cooperation | 1 like

Cool! I'm happy to see this
by Abram Demski on Distributed Cooperation | 0 likes

Caveat: The version of EDT
by 258 on In memoryless Cartesian environments, every UDT po... | 2 likes

[Delegative Reinforcement
by Vadim Kosoy on Stable Pointers to Value II: Environmental Goals | 1 like

Intermediate update: The
by Alex Appel on Further Progress on a Bayesian Version of Logical ... | 0 likes

Since Briggs [1] shows that
by 258 on In memoryless Cartesian environments, every UDT po... | 2 likes

This doesn't quite work. The
by Nisan Stiennon on Logical counterfactuals and differential privacy | 0 likes

I at first didn't understand
by Sam Eisenstat on An Untrollable Mathematician | 1 like


Privacy & Terms