24 search results - page 1 / 5 » The Cross Entropy Method for Fast Policy Search |
84
Voted
ICML
2003
IEEE
15 years 11 months ago
2003
IEEE
We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...
INFORMATICASI
2008
14 years 11 months ago
2008
93
Voted
TSMC
2011
14 years 5 months ago
2011
—This paper introduces an algorithm for direct search of control policies in continuous-state discrete-action Markov decision processes. The algorithm looks for the best closed-l...
94
Voted
AAAI
2010
15 years 10 days ago
2010
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature conv...
75
Voted
WSC
2004
15 years 7 days ago
2004
Global likelihood maximization is an important aspect of many statistical analyses. Often the likelihood function is highly multi-extremal. This presents a significant challenge t...