research
∙
08/16/2023
Planning in the imagination: High-level planning on learned abstract search spaces
We propose a new method, called PiZero, that gives an agent the ability ...
share
research
∙
01/20/2023
Computing equilibria by minimizing exploitability with best-response ensembles
In this paper, we study the problem of computing an approximate Nash equ...
research
∙
11/29/2022
Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks
We study the problem of computing an approximate Nash equilibrium of con...
research
∙
02/24/2020
Efficient exploration of zero-sum stochastic games
We investigate the increasingly important and common game-solving settin...
research
∙
08/31/2017
Differentiable cellular automata
We describe a class of cellular automata (CAs) that are end-to-end diffe...
research
∙
07/09/2017