All seminars take place at noon on Fridays in COB 263 unless otherwise noted.
Re-architecting the Memory-Storage Stack with NVRAMs, Jishen Zhao, UC Santa Cruz
NVRAMs promise new persistent memory technology, which combines attractive attributes from both main memory (fast, load/store interface) and storage (data persistence). However, supporting persistence in the memory requires rethinking of memory system design; the well-studied memory hierarchy design is no longer well-suited to this new scenario. This talk will show our recent work on optimizing the performance of persistent memory systems with new memory control schemes and memory hierarchy design.
Jishen Zhao is an assistant professor in Computer Engineering of UCSC. Her research primarily falls in the areas of computer architecture and electronic design automation, with an emphasis on memory and storage system design, energy efficiency, and high-performance computing. Before joining UCSC, she was a Research Scientist at HP Labs, Palo Alto. Her research on persistent memory received the Best Paper Honorable Mention Award at MICRO 2013.
Learning Plan Abstractions and Coordination for Agents in Real-Time Complex Game Environments, Arnav Jhala, UC Santa Cruz
Player modeling in video games with complex environment and task models is a broad research area. This talk covers two aspects of player modeling : learning plan abstractions from observations of expert humans, and models of cooperation. First, I discuss learning plan abstractions of expert players in StarCraft. Real-Time Strategy (RTS) gameplay exhibits both cognitive complexity and task environment complexity. Expert StarCraft gameplay involves many cognitive processes including estimation, anticipation, and adaptation. One approach to handling this complexity is to learn plan structures from observation of expert gameplay in competitive settings. We show that application of Generalized Sequence Mining algorithms to StarCraft replays results in automated extraction of tactical and strategic patterns that can be encoded in HTN-like plan structures. Next, I discuss belief models of inconsistent collaborators in a multi-agent domain. Maintaining an accurate set of beliefs in a partially observable scenario, particularly with respect to other agents operating in the same space, is a vital aspect of multi-agent planning. We analyze how the beliefs of an agent can be updated for fast adaptivity to changes in the behavior of an unknown teammate. Our results on a variation of the pursuit domain suggest the possibility of approximating a higher-level model by utilizing a belief distribution over a set of lower-level behaviors, particularly when the belief update strategy identifies changes in the behavior in a responsive manner.
Arnav Jhala is an Associate Professor of Computational Media at the University of California, Santa Cruz. His research interests lie at the intersection of artificial intelligence and digital media, particularly in the areas of Computational Cinematography, Reasoning under Uncertainty in Complex Real-time Domains, and Computational Storytelling. At UCSC he directs the Computational Cinematics Studio, and teaches graduate and undergraduate courses in game design, game AI, game engine programming, interactive narratives, and computational cinematography. Arnav holds Ph.D. and M.S. degrees in Computer Science from North Carolina State University, USA (2004, 2009), and B.Eng. in Computer Engineering from Gujarat University, India (2001). He has previously worked at the IT University of Copenhagen, Virtual Heroes, Duke University, the Institute of Creative Technologies at the University of Southern California, and the Indian Space Research Organization (ISRO).
DeepDive: A Data System for Macroscopic Science, Christopher Re, Stanford University