J
Janusz Marecki
Researcher at IBM
Publications - 63
Citations - 2548
Janusz Marecki is an academic researcher from IBM. The author has contributed to research in topics: Stackelberg competition & Markov decision process. The author has an hindex of 21, co-authored 62 publications receiving 2360 citations. Previous affiliations of Janusz Marecki include University of Southern California.
Papers
More filters
Proceedings ArticleDOI
Playing games for security: an efficient exact algorithm for solving Bayesian Stackelberg games
Praveen Paruchuri,Jonathan P. Pearce,Janusz Marecki,Milind Tambe,Fernando Ordóñez,Sarit Kraus +5 more
TL;DR: This paper considers Bayesian Stackelberg games, in which the leader is uncertain about the types of adversary it may face, and presents an efficient exact algorithm for finding the optimal strategy for the leader to commit to in these games.
Proceedings ArticleDOI
Deployed ARMOR protection: the application of a game theoretic model for security at the Los Angeles International Airport
James Pita,Manish Jain,Janusz Marecki,Fernando Ordóñez,Christopher Portway,Milind Tambe,Craig Western,Praveen Paruchuri,Sarit Kraus +8 more
TL;DR: A software assistant agent called ARMOR (Assistant for Randomized Monitoring over Routes) is described that casts this patrolling/monitoring problem as a Bayesian Stackelberg game, allowing the agent to appropriately weigh the different actions in randomization, as well as uncertainty over adversary types.
Posted Content
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
TL;DR: In this paper, the authors introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemma but also require agents to learn policies that implement their strategic intentions.
Proceedings ArticleDOI
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
TL;DR: This work analyzes the dynamics of policies learned by multiple self-interested independent learning agents, each using its own deep Q-network on two Markov games and characterize how learned behavior in each domain changes as a function of environmental factors including resource abundance.
Journal ArticleDOI
GUARDS and PROTECT: next generation applications of security games
TL;DR: An overview of two recent applications of security games is provided and new features and challenges introduced in the new applications are described.