Online Symbolic Gradient-Based Optimization for Factored Action MDPs

By Hao Cui, Roni Khardon. 2016

28 citations recorded by the source corpus.

How researchers see this paper

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

1. Yash Chandak
2. Georgios Theocharous
3. Vaishak Belle
4. Philip S. Thomas
5. Martin Mladenov
6. Emma Jordan
7. Kristian Kersting
8. Hao Cui

Citations in the corpus

• The Symbolic Interior Point Method (2016, methodology): “In particular, the use of ADDs for compactly specifying (and solving) Markov decision processes (i.e. representing transitions and rewards as Boolean functions) was popularized in (Hoey et al. 1999); see (Zamani et al. 2013; Cui and Khardon 2016) for recent offerings.”
• Lifted Stochastic Planning, Belief Propagation and Marginal MAP (2018, methodology): “To control the run time needed for these experiments the algorithms are given 10 seconds per time step (compared to 60 seconds in (Cui and Khardon 2016)).”
• Learning Action Representations for Reinforcement Learning (2019, background): “For planning problems, Cui and Khardon [2016, 2018] showed how a gradient based search on a symbolic representation of the state-action value function can be used to address scalability issues.”