3 search results - page 1 / 1 » Variable Metric Reinforcement Learning Methods Applied to th... |
EWRL
2008
13 years 6 months ago
2008
Two variable metric reinforcement learning methods, the natural actor-critic algorithm and the covariance matrix adaptation evolution strategy, are compared on a conceptual level a...
HIS
2004
13 years 6 months ago
2004
: This work presents a new hybrid neuro-fuzzy model for automatic learning of actions taken by agents. The main objective of this new model is to provide an agent with intelligence...
ICML
2001
IEEE
14 years 5 months ago
2001
IEEE
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...