A survey of point-based POMDP solvers

By Guy Shani, Joelle Pineau, Roberta Kaplow. 2012

Subfields: 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 Reinforcement Learning

1. Sergey Levine
2. Pieter Abbeel
3. Chelsea Finn
4. Nicolas Manfred Otto Heess
5. Timothy P. Lillicrap
6. Shixiang Shane Gu
7. Ofir Nachum
8. Shimon Whiteson

Citations in the corpus

• Memory-based control with recurrent neural networks (2015, background): “This approach has two major disadvantages: The first is the need for a model, and the second is the computational cost that is typically associated with the update of the belief state [8, 23].”
• Control: A perspective (2014, methodology): “An example is the control of partially observed systems, which is now one of the mainstays of machine learning and artificial intelligence [596], as noted in Section 4.”
• Learning deep neural network policies with continuous memory states (2015, background): “Discrete partially observed tasks have been tackled using a variety of reinforcement learning and dynamic programming methods [11], [1].”
• Learning to plan with uncertain topological maps (2020, unknown): “For a thorough discussion on existing solvers for POMDPs, the reader can refer to [47].”