Question: how can we use planning in the Lewis Signaling Game.
Question: When is the RL update rule a regression ? [Something I heard explained in a couple of talks.]
Question: If I take some problems that can be solved with dynamic programming, does tha mean (tabular) RL algs should be able to solve them?
Question: In the Lewis signaling game, how can we test the robustness of an equilibrium? What are the factors that affect the stability of the equilibrium?
Questions: In the lewis signaling game, how does the distribution of state relate to the stability or robustness of the equilibrium
Citation
BibTeX citation:
@online{bochman2025,
author = {Bochman, Oren},
title = {Research {Notes}},
date = {2025-01-06},
url = {https://orenbochman.github.io/posts/2025/2025-01-06-research-notes/},
langid = {en}
}
For attribution, please cite this work as:
Bochman, Oren. 2025. “Research Notes.” January 6, 2025. https://orenbochman.github.io/posts/2025/2025-01-06-research-notes/.