Sciweavers

251 search results - page 6 / 51
» Reducing the Knowledge Tracing Space
Sort
View
ICML
2004
IEEE
15 years 10 months ago
Learning to fly by combining reinforcement learning with behavioural cloning
Reinforcement learning deals with learning optimal or near optimal policies while interacting with the environment. Application domains with many continuous variables are difficul...
Eduardo F. Morales, Claude Sammut
65
Voted
SIGMETRICS
1994
ACM
113views Hardware» more  SIGMETRICS 1994»
15 years 1 months ago
Shade: A Fast Instruction-Set Simulator for Execution Profiling
Shade is an instruction-set simulator and custom trace generator. Application programs are executed and traced under the control of a user-supplied trace analyzer. To reduce commu...
Robert F. Cmelik, David Keppel
64
Voted
HIPC
2005
Springer
15 years 3 months ago
Application of Reduce Order Modeling to Time Parallelization
We recently proposed a new approach to parallelization, by decomposing the time domain, instead of the conventional space domain. This improves latency tolerance, and we demonstrat...
Ashok Srinivasan, Yanan Yu, Namas Chandra
72
Voted
WSC
2000
14 years 10 months ago
Facilitating level three cache studies using set sampling
We discuss some of the difficulties present in trace collection and trace-driven cache simulation. We then describe our multiprocessor tracing technique and verify that it accurat...
Niki C. Thornock, J. Kelly Flanagan
AAAI
2006
14 years 11 months ago
Simultaneous Team Assignment and Behavior Recognition from Spatio-Temporal Agent Traces
This paper addresses the problem of activity recognition for physically-embodied agent teams. We define team activity recognition as the process of identifying team behaviors from...
Gita Sukthankar, Katia P. Sycara