Timezone: »
Computer games sales are three time larger than industry software sales, and on par with Hollywood box office sales. Modern computer games are often based on extremely complex simulations of the real world and constitute one of the very few real fields of application for artificial intelligence encountered in everyday live. Surprisingly, machine learning methods are not present in the vast majority of computer games. There have been a few recent and notable successes in turn-based two-player, discrete action space games such as Backgammon, Checkers, Chess and Poker. However, these successes are in stark contrast to the difficulties still encountered in the majority of computer games, which typically involve more than two agents choosing from a continuum of actions in complex artificial environments. Typical game AI is still largely built around fixed systems of rules that often result in implausible or predictable behaviour and poor user experience. The purpose of this workshop is to involve the NIPS community in the exciting challenges that games - ranging from traditional table top games to cutting-edge console and PC games - offer to machine learning.
Author Information
Joaquin Quiñonero-Candela (LinkedIn)
Thore K Graepel (Microsoft Research Cambridge (UK))
Ralf Herbrich (Hasso Plattner Institute)
More from the Same Authors
-
2018 Workshop: NeurIPS 2018 Competition Track Day 2 »
Ralf Herbrich · Sergio Escalera -
2018 Workshop: NeurIPS 2018 Competition Track Day 1 »
Sergio Escalera · Ralf Herbrich -
2018 : Opening and Best Demo Award announcement »
Sergio Escalera · Ralf Herbrich -
2017 Workshop: Machine Learning on the Phone and other Consumer Devices »
Hrishikesh Aradhye · Joaquin Quinonero Candela · Rohit Prasad -
2014 Workshop: Software Engineering for Machine Learning »
Joaquin Quiñonero-Candela · Ryan D Turner · Xavier Amatriain -
2013 Workshop: Resource-Efficient Machine Learning »
Yevgeny Seldin · Yasin Abbasi Yadkori · Yacov Crammer · Ralf Herbrich · Peter Bartlett -
2013 Workshop: Probabilistic Models for Big Data »
Neil D Lawrence · Joaquin Quiñonero-Candela · Tianshi Gao · James Hensman · Zoubin Ghahramani · Max Welling · David Blei · Ralf Herbrich -
2013 Session: Tutorial Session B »
Joaquin Quiñonero-Candela -
2012 Demonstration: DIRTBIS - Distributed Real-Time Bayesian Inference Service »
Ralf Herbrich -
2008 Workshop: Beyond Search: Computational Intelligence for the Web (day 2) »
Anton Schwaighofer · Junfeng Pan · Thomas Borchert · Olivier Chapelle · Joaquin Quiñonero-Candela -
2008 Workshop: Beyond Search: Computational Intelligence for the Web (day 1) »
Anton Schwaighofer · Junfeng Pan · Thomas Borchert · Olivier Chapelle · Joaquin Quiñonero-Candela -
2007 Poster: TrueSkill Through Time: Revisiting the History of Chess »
Pierre Dangauthier · Ralf Herbrich · Tom Minka · Thore K Graepel -
2007 Spotlight: TrueSkill Through Time: Revisiting the History of Chess »
Pierre Dangauthier · Ralf Herbrich · Tom Minka · Thore K Graepel -
2007 Demonstration: Learning To Race by Model-Based Reinforcement Learning with Adaptive Abstraction »
Thore K Graepel · Phil A Trelford · Ralf Herbrich · Mykel J Kochenderfer -
2006 Workshop: Learning when test and training inputs have different distributions »
Joaquin Quiñonero-Candela · Masashi Sugiyama · Anton Schwaighofer · Neil D Lawrence -
2006 Poster: TrueSkill: A Bayesian Skill Rating System »
Ralf Herbrich · Tom Minka · Thore K Graepel -
2006 Talk: TrueSkill: A Bayesian Skill Rating System »
Ralf Herbrich · Tom Minka · Thore K Graepel