595 search results - page 46 / 119 » Predictive State Representations with State Space Partitioni... |
115
click to vote
IJRR
2011
14 years 5 months ago
2011
Abstract Partially observable Markov decision processes (POMDPs) are a principled mathematical framework for planning under uncertainty, a crucial capability for reliable operation...
Publication
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
AIPS
2008
15 years 29 days ago
2008
The heuristics used for planning and search often take the pattern databases generated from abstracted versions of the given state space. Pattern databases are typically stored p ...
ICTAI
2010
IEEE
14 years 8 months ago
2010
IEEE
Abstract--The difficulties encountered in sequential decisionmaking problems under uncertainty are often linked to the large size of the state space. Exploiting the structure of th...
ICAI
2009
14 years 8 months ago
2009
- We address the issues of improving the feature generation methods for the value-function approximation and the state space approximation. We focus the improvement of feature gene...