Sciweavers

49 search results - page 3 / 10
» Model-based Policy Gradient Reinforcement Learning
Sort
View
ICMLA
2010
13 years 3 months ago
Multimodal Parameter-exploring Policy Gradients
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...
Frank Sehnke, Alex Graves, Christian Osendorfer, J...
ECML
2005
Springer
13 years 11 months ago
Natural Actor-Critic
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...
Jan Peters, Sethu Vijayakumar, Stefan Schaal
NIPS
2001
13 years 7 months ago
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
NIPS
1998
13 years 7 months ago
Gradient Descent for General Reinforcement Learning
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
Leemon C. Baird III, Andrew W. Moore
AAAI
2010
13 years 7 months ago
Relative Entropy Policy Search
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature conv...
Jan Peters, Katharina Mülling, Yasemin Altun