Search filters

List of works by Michael Bowling

Actor-Critic Policy Optimization in Partially Observable Multiagent Environments

Computer science. Heads-up limit hold'em poker is solved

scientific article

Computing Robust Counter-Strategies

scientific article published in January 2008

Context Tree Switching

Convergence and No-Regret in Multiagent Learning

scientific article published in January 2005

DeepStack: Expert-level artificial intelligence in heads-up no-limit poker.

scientific article published on 2 March 2017

Ease-of-Teaching and Language Structure from Emergent Communication

scientific article published in January 2019

Linear Fitted-Q Iteration with Multiple Reward Functions

scientific article published on November 2012

Machine learning and games

scholarly article by Michael Bowling et al published 10 May 2006 in Machine Learning

Monte Carlo Sampling for Regret Minimization in Extensive Games

scientific article published in January 2009

Online Discovery and Learning of Predictive State Representations

scientific article published in January 2006

Regret Minimization in Games with Incomplete Information

scientific article published in January 2008

Sketch-Based Linear Value Function Approximation

scientific article published in January 2012

Stable Dual Dynamic Programming

scientific article published in January 2008

Strategy Grafting in Extensive Games

scientific article published in January 2009

The CMUnited-98 champion small-robot team

journal article; published in Advanced Robotics in 1998

The Forget-me-not Process

scientific article published in January 2016

Tractable Objectives for Robust Policy Optimization

scientific article published in January 2012

Variance Reduction in Monte-Carlo Tree Search

scientific article published in January 2011

iLSTD: Eligibility Traces and Convergence Analysis

scientific article published in January 2007