AISC5 Retrospective: Mechanisms for Avoiding Tragedy of the Commons in Common Pool Resource Problems 2021-09-27T16:46:40.389Z

Comment by bengr (_meta) on AISC5 Retrospective: Mechanisms for Avoiding Tragedy of the Commons in Common Pool Resource Problems · 2021-09-29T03:03:04.785Z · LW · GW

Yes, reputation was automatically updated each time step.

We thought it would make sense to decrease reputation for "unsustainable" and "violent" behaviors (e.g. over-harvesting apples, tagging other agents) and increase reputation for "sustainable" and "peaceful" behaviors. But these rules were all hardcoded.

Comment by bengr (_meta) on April 15, 2040 · 2021-05-05T21:17:31.435Z · LW · GW

"But you're a stronger assistant than most people in my tax bracket have. Doesn't that give you an edge in negotiation?"

"The other assistants and I are using a negotiation protocol in which smarter agents are on an equal footing with dumber agents. Of course, people with less capable assistants would never agree to a protocol that puts them at a disadvantage."

I'm interested in what this negotiation protocol would look like. If one agent is "smarter" than its counterparts, what would prevent it from negotiating a more favorable outcome for its principal?