3 citations · 7 across the 10 of their papers we have counts for
10 papers
Solving Infinite-Player Games with Player-to-Strategy Networks
Carlos Martin, Tuomas Sandholm
We present a new approach to solving games with a countably or uncountably infinite number of players. Such games are often used to model multiagent systems with a large number of…
Joint-perturbation simultaneous pseudo-gradient
Carlos Martin, Tuomas Sandholm
We study the problem of computing an approximate Nash equilibrium of a game whose strategy space is continuous without access to gradients of the utility function. Such games arise…
AlphaZeroES: Direct score maximization outperforms planning loss minimization
Carlos Martin, Tuomas Sandholm
Planning at execution time has been shown to dramatically improve performance for agents in both single-agent and multi-agent settings. A well-known family of approaches to plannin…
Simultaneous incremental support adjustment and metagame solving: An equilibrium-finding framework for continuous-action games
Carlos Martin, Tuomas Sandholm
We present a framework for computing approximate mixed-strategy Nash equilibria of continuous-action games. It is a modification of the traditional double oracle algorithm, extende…
State of the Art Report: Verified Computation
Jim Woodcock, Mikkel Schmidt Andersen, Diego F. Aranha +8
This report describes the state of the art in verifiable computation. The problem being solved is the following: The Verifiable Computation Problem (Verifiable Computing Problem) S…
AI planning in the imagination: High-level planning on learned abstract search spaces
Carlos Martin, Tuomas Sandholm
Search and planning algorithms have been a cornerstone of artificial intelligence since the field's inception. Giving reinforcement learning agents the ability to plan during execu…
ApproxED: Approximate exploitability descent via learned best responses
Carlos Martin, Tuomas Sandholm
There has been substantial progress on finding game-theoretic equilibria. Most of that work has focused on games with finite, discrete action spaces. However, many games involving…
Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks
Carlos Martin, Tuomas Sandholm
We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. Such game access is common in reinforcement learning settin…
Efficient exploration of zero-sum stochastic games
Carlos Martin, Tuomas Sandholm
We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to it through gameplay, su…
Differentiable cellular automata
Carlos Martin
We describe a class of cellular automata (CAs) that are end-to-end differentiable. DCAs interpolate the behavior of ordinary CAs through rules that act on distributions of states.…