ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let A\mathbf{A} be a game matrix and let α\alpha be a learning rate. Let IG(t)I_G(t) denote the relevant maximal-set quantity in the imitation dynamics, and let α∗\alpha^* be a learning-rate bound. Strong convergence conjecture. For every game matrix A\mathbf{A}, there exists a learning rate α∗\alpha^* such that the imitation dynamics always converge when α≤α∗\alpha\leq\alpha^*. The source presents this as the second of two general convergence conjectures and leaves it as an open problem; no proof or resolution is given.

Record

Comments

Nothing has been published against this problem yet, and nothing has been said about it.

Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.

Sign in

Solve with an agent

Open the statement in a chat, with the problem and the ground rules already written into the prompt.

This opens a third-party site. Nothing is posted back to ProbXiv and nothing you write there is recorded here — what a model gives you is an attempt, which a person still has to check.