233 search results - page 23 / 47 » Composing and combining policies under the policy machine |
156
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
High dimensionality of POMDP's belief state space is one major cause that makes the underlying optimal policy computation intractable. Belief compression refers to the method...
161
click to vote
HPDC
2010
IEEE
15 years 7 months ago
2010
IEEE
Clusters are mostly used through Resources Management Systems (RMS) with a static allocation of resources for a bounded amount of time. Those approaches are known to be insufficie...
177
click to vote
GECCO
2000
Springer
15 years 9 months ago
2000
Springer
Reinforcement learning (RL) is one of the machine learning techniques and has been received much attention as a new self-adaptive controller for various systems. The RL agent auto...
205
click to vote
IPPS
2010
IEEE
15 years 4 months ago
2010
IEEE
Abstract--The now commonplace multi-core chips have introduced, by design, a deep hierarchy of memory and cache banks within parallel computers as a tradeoff between the user frien...
158
click to vote
ICML
1998
IEEE
16 years 6 months ago
1998
IEEE
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...