Publikation
Policy Gradients with Parameter-Based Exploration for Control
Frank Sehnke; Christian Osendorfer; Thomas Rückstieß; Alex Graves; Jan Peters; Jürgen Schmidhuber
In: Vera Kurková; Roman Neruda; Jan Koutník (Hrsg.). Artificial Neural Networks - ICANN 2008 , 18th International Conference, Proceedings. International Conference on Artificial Neural Networks (ICANN-2008), September 3-6, Prague, Czech Republic, Pages 387-396, Lecture Notes in Computer Science, Vol. 5163, Springer, 2008.
Zusammenfassung
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than those obtained by policy gradient methods such as REINFORCE. For several complex control tasks, including robust standing with a humanoid robot, we show that our method outperforms well-known algorithms from the fields of policy gradients, finite difference methods and population based heuristics. We also provide a detailed analysis of the differences between our method and the other algorithms.