Policy Gradients with Parameter-Based Exploration for Control

  title={Policy Gradients with Parameter-Based Exploration for Control},
  author={Frank Sehnke and Christian Osendorfer and Thomas R{\"u}ckstie\ss and Alex Graves and Jan Peters and J{\"u}rgen Schmidhuber},
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… CONTINUE READING
Highly Cited
This paper has 48 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 33 extracted citations

Similar Papers

Loading similar papers…