Reinforcement learning for factored Markov decision processes

By Geoffrey E. Hinton, Brian Sallans. 2002

34 citations recorded by the source corpus.

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. Nicolas Manfred Otto Heess
4. Timothy P. Lillicrap
5. David Silver
6. Shimon Whiteson
7. Ofir Nachum
8. Shixiang Shane Gu

Citations in the corpus

• Memory-based control with recurrent neural networks (2015, methodology): “ible to use truncated BPTT, although we do not use this here. The full algorithm is given below (Algorithm 1). RDPG is an algorithm for learning deterministic policies. As discussed in the literature [25, 20] it is possible to construct examples where deterministic policies perform poorly under part”
• A Latent Variable Model for Generative Dependency Parsing (2007, methodology): “Sigmoid Belief Networks (SBNs) were used originally for character recognition tasks, but later a dynamic modification of this model was applied to the reinforcement learning task (Sallans, 2002).”
• Incremental Sigmoid Belief Networks for Grammar Learning (2010, methodology): “DBNs based on sigmoid belief networks were considered in Sallans (2002) in the context of reinforcement learning.”
• Constituent Parsing with Incremental Sigmoid Belief Networks (2007, methodology): “Sigmoid Belief Networks were used originally for character recognition tasks, but later a dynamic modification of this model was applied to the reinforcement learning task (Sallans, 2002).”