51 search results - page 1 / 11 » Improving Approximate Value Iteration Using Memories and Pre... |
AAAI
2006
13 years 8 months ago
2006
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
IWMM
2010
Springer
13 years 11 months ago
2010
Springer
With the availability of chip multiprocessor (CMP) and simultaneous multithreading (SMT) machines, extracting thread level parallelism from a sequential program has become crucial...
SARA
2005
Springer
14 years 14 days ago
2005
Springer
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...
IJCAI
2003
13 years 8 months ago
2003
We present an approximate policy iteration algorithm that uses rollouts to estimate the value of each action under a given policy in a subset of states and a classifier to general...
AAAI
2006
13 years 8 months ago
2006
We study how to find plans that maximize the expected total utility for a given MDP, a planning objective that is important for decision making in high-stakes domains. The optimal...