Reinforcement Learning in Continuous State and Action Spaces

By Hado van Hasselt. 2012

100 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

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. Xue Bin Peng
2. Michiel van de Panne
3. Glen Berseth
4. KangKang Yin
5. Sergey Levine
6. Pieter Abbeel
7. Chelsea Finn
8. Deepak Pathak

In Computational Theory and Mathematics

1. Michiel van de Panne
2. Glen Berseth
3. KangKang Yin
4. Xue Bin Peng
5. Sergey Levine

Citations in the corpus

• DeepLoco (2017, methodology): “Policy improvement is performed using a CACLA-style positive temporal difference update [Van Hasselt 2012].”
• Dynamic terrain traversal skills using reinforcement learning (2015, methodology): “A good discussion of the specific challenges that are presented by continuous action spaces is given by van Hasselt et al. [Van Hasselt and Wiering 2007; Van Hasselt 2012].”