C
Craig Boutilier
Researcher at Google
Publications - 301
Citations - 21904
Craig Boutilier is an academic researcher from Google. The author has contributed to research in topics: Markov decision process & Regret. The author has an hindex of 68, co-authored 301 publications receiving 20785 citations. Previous affiliations of Craig Boutilier include University of Toronto & University of British Columbia.
Papers
More filters
Journal ArticleDOI
Decision-theoretic planning: structural assumptions and computational leverage
TL;DR: In this article, the authors present an overview and synthesis of MDP-related methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI.
Proceedings Article
The dynamics of reinforcement learning in cooperative multiagent systems
Caroline Claus,Craig Boutilier +1 more
TL;DR: This work distinguishes reinforcement learners that are unaware of (or ignore) the presence of other agents from those that explicitly attempt to learn the value of joint actions and the strategies of their counterparts, and proposes alternative optimistic exploration strategies that increase the likelihood of convergence to an optimal equilibrium.
Journal ArticleDOI
CP-nets: a tool for representing and reasoning with conditional ceteris paribus preference statements
TL;DR: This paper proposes a qualitative graphical representation of preferences that reflects conditional dependence and independence of preference statements under a ceteris paribus (all else being equal) interpretation, and provides a formal semantics for this model.
Posted Content
Context-Specific Independence in Bayesian Networks
TL;DR: In this paper, the authors propose a formal notion of context-specific independence (CSI) based on regularities in the conditional probability tables (CPTs) at a node, and then focus on a particular qualitative representation scheme -tree-structured CPTs -for capturing CSI.
Proceedings Article
Context-specific independence in Bayesian networks
TL;DR: This paper proposes a formal notion of context-specific independence (CSI), based on regularities in the conditional probability tables (CPTs) at a node, and proposes a technique, analogous to (and based on) d-separation, for determining when such independence holds in a given network.