UMD     This Site

In recent years, the Go-playing artificial intelligence AlphaGo and its successors AlphaGo Zero and AlphaZero have made international headlines with their incredible successes in game playing. They are part of a line of AI systems developed to beat humans at games like Go, checkers, chess, Scrabble and Jeopardy. Each successive challenge extends the boundaries of machine learning and its capabilities. The programs have been touted as evidence of the immense potential of artificial intelligence, and in particular, machine learning.

At the core of AlphaGo and its successors are the ideas related to adaptive multistage sampling (AMS) simulation-based algorithms for Markov decision processes (MDPs) first explored by four University of Maryland researchers in a 2005 Operations Research paper. Now, one of the researchers, Professor Michael C. Fu (BMGT/ISR), has written “Simulation-Based Algorithms for Markov Decision Processes: Monte Carlo Tree Search from AlphaGo to AlphaZero,” a review of the original ideas and the ensuing developments in the Asia-Pacific Journal of Operational Research, Vol. 36, No. 06, 1940009 (2019).

The deep neural networks of AlphaGo, AlphaZero, and all their incarnations are trained using a technique called Monte Carlo tree search (MCTS), whose roots can be traced back to an AMS simulation-based algorithm for MPDs  published in Operations Research back in 2005.

 “An adaptive sampling algorithm for solving Markov decision processes”  was written by Institute for Systems Research (ISR) Postdoctoral Researcher Hyeong Soo Chang, Professor Michael C. Fu, Electrical and Computer Engineering (ECE) Ph.D. student Jiaqiao Hu, and Professor Steven I. Marcus (ECE/ISR). The idea was introduced even earlier in 2002.

In the current review article, Fu reviews the history and background of AlphaGo through AlphaZero, traces the origins of MCTS back to simulation-based algorithms for MDPs, and examines its role in training the neural networks that essentially carry out the value/policy function approximation used in approximate dynamic programming, reinforcement learning, and neuro-dynamic programming. Fu also includes discussion recently proposed enhancements that build on statistical ranking and selection research in the operations research simulation community.

Related Articles:
Planning and learning algorithms developed for refinement acting engine
Who's walking deceptively? Manocha's team thinks they know.
New affiliate faculty Mark Fuge is expert in machine learning and artificial intelligence
Maryland research contributes to Google’s AlphaGo AI system
A learning algorithm for training robots' deep neural networks to grasp novel objects
ISR alum honors former advisor Benjamin Kedem with quantile frequency analysis paper
Forecasting traffic for autonomous vehicles
ISR, ECE, CS, UMIACS faculty present 12 talks at Northrop Grumman University Research Symposium
Advancing Healthcare through Robotics and Machine Learning
Machine Learning's Translational Medicine

December 17, 2019

«Previous Story  



Current Headlines

In Race With Virus, Researchers Speed Development of Medical Equipment

GAMMA Group's Research on Emotional Modeling and Social Robotics Featured in Forbes

Srivastava wins NSF funding for integrated circuit fabrication security

Protection Collections Abound for Local Health Care Workers

New U.S. Patent: Integrated Onboard Chargers for Plug-In Vehicles

Public health planners: Free resources for emergency health clinics

Planning and learning algorithms developed for refinement acting engine

Clark School Engineers Create Solutions for a Crisis

COVID-19 Decision Making Gets a Big Data Boost

Researchers from Poland report results aided by UMD's AIM Lab

Back to top  
Home Clark School Home UMD Home