656 search results - page 76 / 132 » Complexity of finite-horizon Markov decision process problem... |
129
click to vote
ICN
2007
Springer
15 years 8 months ago
2007
Springer
— In this paper, we use the Markov Decision Process (MDP) technique to find the optimal code allocation policy in High-Speed Downlink Packet Access (HSDPA) networks. A discrete ...
135
click to vote
EWRL
2008
15 years 3 months ago
2008
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
UAI
2004
15 years 3 months ago
2004
We present a major improvement to the incremental pruning algorithm for solving partially observable Markov decision processes. Our technique targets the cross-sum step of the dyn...
139
click to vote
ISAAC
2010
Springer
14 years 12 months ago
2010
Springer
Howard's policy iteration algorithm is one of the most widely used algorithms for finding optimal policies for controlling Markov Decision Processes (MDPs). When applied to we...
151
click to vote
JMLR
2010
14 years 8 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...