875 search results - page 63 / 175 » A New Approach for Testing Properties of Discrete Distributi... |
136
click to vote
ECML
2007
Springer
15 years 10 months ago
2007
Springer
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
171
click to vote
SP
2005
IEEE
15 years 10 months ago
2005
IEEE
The low-cost, off-the-shelf hardware components in unshielded sensor-network nodes leave them vulnerable to compromise. With little effort, an adversary may capture nodes, analyze...
139
click to vote
CAV
2004
Springer
15 years 10 months ago
2004
Springer
—We introduce a new BDD-like data structure called Hybrid-Restriction Diagrams (HRDs) for the representation and manipulation of linear hybrid automata (LHA) state-spaces and pre...
115
Voted
DCG
2006
15 years 4 months ago
2006
This paper sheds a new light on the split decomposition theory and T-theory from the viewpoint of convex analysis and polyhedral geometry. By regarding finite metrics as discrete ...
153
click to vote
PPSN
2004
Springer
15 years 10 months ago
2004
Springer
Abstract. This paper describes a new approach for parameter optimization that uses a novel representation for the parameters to be optimized. By using genetic programming, the new ...