91 search results - page 1 / 19 » Parameter-exploring policy gradients |
ICANN
2010
Springer
13 years 5 months ago
2010
Springer
Abstract. Developing superior artificial board-game players is a widelystudied area of Artificial Intelligence. Among the most challenging games is the Asian game of Go, which, des...
NECO
2010
13 years 3 months ago
2010
Most conventional Policy Gradient Reinforcement Learning (PGRL) algorithms neglect (or do not explicitly make use of) a term in the average reward gradient with respect to the pol...
AAAI
2011
12 years 4 months ago
2011
In environmental and natural resource planning domains actions are taken at a large number of locations over multiple time periods. These problems have enormous state and action s...
NN
2010
Springer
13 years 3 months ago
2010
Springer
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
ICMLA
2010
13 years 2 months ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...