Optimal control theory and the linear bellman equation

By Hilbert J. Kappen. 2011

59 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Control and Systems Engineering, 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. Sergey Levine
2. Pieter Abbeel
3. Jan Peters
4. Marc Toussaint
5. Chelsea Finn
6. Shimon Whiteson
7. Sethu Vijayakumar
8. Konrad Rawlik

In Computer Networks and Communications

1. Sethu Vijayakumar
2. Xu Xu
3. Marc Toussaint
4. Zhao Xu
5. Sergey Levine
6. Songjian Chai
7. Konrad Rawlik
8. Yan Xu

In Control and Systems Engineering

1. Sergey Levine
2. Marc Toussaint
3. Sethu Vijayakumar
4. Konrad Rawlik
5. Pieter Abbeel
6. Chelsea Finn
7. Xu Xu
8. Zhao Xu

In Reinforcement Learning

1. Sergey Levine
2. Pieter Abbeel
3. Marc Toussaint
4. Chelsea Finn
5. Jan Peters
6. Shixiang Shane Gu
7. Shimon Whiteson
8. E. Todorov

Citations in the corpus

• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review (2018, methodology): “theentireframeworkto operateentirelyonstates ratherthanactions. This gives rise to a simple and elegant frameworkthat is especially tractable in the tabular setting. In the domain of optimal control, Kappen (2011) formulateda class of path integral control problems that alsocorrespondtothegraphicalm”
• Path Integral Control by Reproducing Kernel Hilbert Space Embedding (2012, methodology): “In this section we briefly review the path integral approach to stochastic optimal control as proposed by [Kappen, 2005] (see also [Kappen, 2011; Theodorou et al., 2010]).”
• A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management (2020, methodology): “The optimal Q-value Q∗π (st, at) can be obtained by using Bellman equation [33], given as below,”