Policy Gradients with Parameter-Based Exploration for Control

Frank Sehnke(Technical University of Munich), Jürgen Schmidhuber(Dalle Molle Institute for Artificial Intelligence Research), Alex Graves(Google DeepMind (United Kingdom)), Thomas Rückstieß(Technical University of Munich), Christian Osendorfer(Technical University of Munich), Jan Peters(Technische Universität Darmstadt)
Lecture notes in computer science
September 5, 2008
Cited by 60


Related Papers

Playing Atari with Deep Reinforcement Learning
|arXiv (Cornell University)|2013|5.1k
Reinforcement learning in robotics: A survey
|The International Journal of Robotics Research|2013|3.1k
Natural Actor-Critic
|Neurocomputing|2008|751