2914 search results - page 227 / 583 » Optimization by Stochastic Continuation |
197
click to vote
AAAI
2007
15 years 9 months ago
2007
In timed, zero-sum games, the goal is to maximize the probability of winning, which is not necessarily the same as maximizing our expected reward. We consider cumulative intermedi...
174
click to vote
AAAI
1996
15 years 7 months ago
1996
Agents can benefit from contracting some of their tasks that cannot be performedby themselves or that can be performed moreefficiently by other agents. Developing an agent's ...
177
click to vote
ML
2002
ACM
15 years 6 months ago
2002
ACM
An issue that is critical for the application of Markov decision processes MDPs to realistic problems is how the complexity of planning scales with the size of the MDP. In stochas...
183
click to vote
COLT
2010
Springer
15 years 4 months ago
2010
Springer
Multiarmed bandit problem is a typical example of a dilemma between exploration and exploitation in reinforcement learning. This problem is expressed as a model of a gambler playi...
179
click to vote
INFOCOM
2010
IEEE
15 years 4 months ago
2010
IEEE
We propose a distributed mechanism for finding websurfing strategies that is inspired by the StumbleUpon recommendation engine. Each day, a websurfer visits a sequence of websites ...