Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs

By Rowan Thomas McAllister, Carl E. Rasmussen. 2017

37 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. David R Ha
2. J. Urgen Schmidhuber
3. A. Piergiovanni
4. Michael S. Ryoo
5. Sergey Levine
6. Alan Wu
7. Quoc V. Le
8. Kristen Grauman

In Computational Theory and Mathematics

1. David R Ha
2. J. Urgen Schmidhuber
3. Alan Wu
4. Michael S. Ryoo
5. A. Piergiovanni
6. Sergey Levine
7. Jeff Clune
8. Pierre-Yves Oudeyer

In Reinforcement Learning

1. David R Ha
2. Michael S. Ryoo
3. A. Piergiovanni
4. Alan Wu
5. Sergey Levine
6. J. Urgen Schmidhuber
7. Pieter Abbeel
8. Chelsea Finn

Citations in the corpus

• Recurrent World Models Facilitate Policy Evolution (2018, methodology): “The more recent PILCO [10, 53] is a probabilistic model-based search policy method designed to solve difficult control problems.”
• Learning Real-World Robot Policies by Dreaming (2018, methodology): “PILCO [3, 20] uses a Gaussian process (GP) to model the state-transition model and samples many trajectories from it to train a policy.”