Richard Segal

MailCat: an intelligent assistant for organizing e-mail

MailCat is an intelligent assistant that heips users organize their e-mail into folders. It uses a text classifier to learn each user’s mail-filing habits. MailCat uses what it learns to predict the three folders in which the user is most likely to place each incoming message. It then provides shortcut buttons to file each message into one of these three folders. When one of MailCat’s predictions is correct, the effort required to file a message is reduced to a single button click.

Fuego—An Open-Source Framework for Board Games and Go Engine Based on Monte Carlo Tree Search

FUEGO is both an open-source software framework and a state-of-the-art program that plays the game of Go. The framework supports developing game engines for full-information two-player board games, and is used successfully in a substantial number of projects. The FUEGO Go program became the first program to win a game against a top professional player in 9 × 9 Go. It has won a number of strong tournaments against other programs, and is competitive for 19 × 19 as well. This paper gives an overview of the development and current state of the FUEGO project. It describes the reusable components of the software framework and specific algorithms used in the Go engine.

Dynamics of an Information-Filtering Economy

Our overall goal is to characterize and understand the dynamic behavior of information economies: very large open economies of automated information agents that are likely to come into existence on the Internet. Here we model a simple information-filtering economy in which broker agents sell selected articles to a subscribed set of consumers. Analysis and simulation of this model reveal the existence of both desirable and undesirable phenomena, and give some insight into their nature and the conditions under which they occur. In particular, efficient self-organization of the broker population into specialized niches can occur when communication and processing costs are neither too high nor too low, but endless price wars can undermine this desirable state of affairs.

On the scalability of parallel UCT

The parallelization of MCTS across multiple-machines has proven surprisingly difficult. The limitations of existing algorithms were evident in the 2009 Computer Olympiad where ZEN using a single fourcore machine defeated both Fuego with ten eight-core machines, and Mogo with twenty thirty-two core machines. This paper investigates the limits of parallel MCTS in order to understand why distributed parallelism has proven so difficult and to pave the way towards future distributed algorithms with better scaling. We first analyze the single-threaded scaling of Fuego and find that there is an upper bound on the play-quality improvements which can come from additional search. We then analyze the scaling of an idealized N-core shared memory machine to determine the maximum amount of parallelism supported by MCTS. We show that parallel speedup depends critically on how much time is given to each player. We use this relationship to predict parallel scaling for time scales beyond what can be empirically evaluated due to the immense computation required. Our results show that MCTS can scale nearly perfectly to at least 64 threads when combined with virtual loss, but without virtual loss scaling is limited to just eight threads. We also find that for competition time controls scaling to thousands of threads is impossible not necessarily due to MCTS not scaling, but because high levels of parallelism can start to bump up against the upper performance bound of FUEGO itself.

Emergent behavior in information economies

Our overall goal is to characterize and understand the dynamic behavior of very large open economies of automated information agents. Analysis and simulation of a simple information-filtering economy reveal both efficient self-organization of the brokers into specialized niches and endless price wars, depending on extrinsic costs.