71 search results - page 1 / 15 » Relative Entropy Policy Search |
AAAI
2010
13 years 6 months 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...
JMLR
2012
11 years 7 months ago
2012
Many real-world problems are inherently hierarchically structured. The use of this structure in an agent’s policy may well be the key to improved scalability and higher performa...
ICML
2003
IEEE
14 years 5 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...
TSMC
2011
12 years 11 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...
INFORMATICASI
2008
13 years 4 months ago
2008