Truncating Temporal Diierences: on the Eecient Implementation of Td for Reinforcement Learning

By Pawea Cichosz. 1995

How researchers see this paper

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

1. Philip S. Thomas
2. George Dimitri Konidaris
3. Sergey Levine
4. Andrew Barto
5. Richard S. Sutton
6. Scott Niekum
7. Lihong Li
8. Pieter Abbeel

Citations in the corpus

• TD γ : Re-evaluating Complex Backups in Temporal Difference Learning (2011, methodology): “One approach to deriving an incremental algorithm is to use only the first C n-step returns from each state, similar to truncated temporal differences [8].”
• Reinforcement Learning: An Introduction (1998, methodology): “The work of Cichosz (1995) and particularly van Seijen (2016) showed that they are actually completely practical algorithms.”