46 search results - page 3 / 10 » Discretization of Continuous Action Spaces in Extensive-Form... |
ICRA
2009
IEEE
13 years 12 months ago
2009
IEEE
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
UAI
2004
13 years 6 months ago
2004
Although many real-world stochastic planning problems are more naturally formulated by hybrid models with both discrete and continuous variables, current state-of-the-art methods ...
JACM
2007
13 years 5 months ago
2007
abstraction of imperfect information games ANDREW GILPIN and TUOMAS SANDHOLM Computer Science Department Carnegie Mellon University Pittsburgh, PA, USA Finding an equilibrium of an...
SIGECOM
2006
ACM
13 years 11 months ago
2006
ACM
Finding an equilibrium of an extensive form game of imperfect information is a fundamental problem in computational game theory, but current techniques do not scale to large games...
JMLR
2006
13 years 5 months ago
2006
We propose a novel approach to optimize Partially Observable Markov Decisions Processes (POMDPs) defined on continuous spaces. To date, most algorithms for model-based POMDPs are ...