14 search results - page 2 / 3 » Sensitive Discount Optimality: Unifying Discounted and Avera... |
COLT
2007
Springer
13 years 11 months ago
2007
Springer
Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, t...
ECML
2004
Springer
13 years 11 months ago
2004
Springer
Although tabular reinforcement learning (RL) methods have been proved to converge to an optimal policy, the combination of particular conventional reinforcement learning techniques...
CORR
2006
Springer
13 years 5 months ago
2006
Springer
While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. Optimal decision thresholds ...
ICML
1999
IEEE
14 years 6 months ago
1999
IEEE
Consider the task of exploring the Web in order to find pages of a particular kind or on a particular topic. This task arises in the construction of search engines and Web knowled...
BROADNETS
2004
IEEE
13 years 9 months ago
2004
IEEE
The scarcity and large fluctuations of link bandwidth in wireless networks have motivated the development of adaptive multimedia services in mobile communication networks, where i...