Incremental Basis Construction from Temporal Difference Error

By Yi Sun, Faustino J. Gomez, Mark B. Ring, J. Urgen Schmidhuber. 2011

19 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. David Silver
4. Marc G. Bellemare
5. Tom Schaul
6. John Quan
7. Wendelin Böhmer
8. R´emi Munos

Citations in the corpus

• Prioritized Experience Replay (2015, methodology): “TD-errors have also been used as a prioritization mechanism for determining where to focus resources, for example when choosing where to explore (White et al., 2014) or which features to select (Geramifard et al., 2011; Sun et al., 2011).”
• Construction of approximation spaces for reinforcement learning (2013, background): “This is motivated by Drazin bases and has been reported to reduce the number of required features for large γ. Recently, Sun et al. (2011) have pointed out that given some basis Φ k , the best k + 1'th basis function is always the fixed point solution with the current Bellman error, that is, the…”