Problem solving with reinforcement learning

By Gavin Adrian Rummery. 1995

How researchers see this paper

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

1. Sergey Levine
2. Richard S. Sutton
3. Hado van Hasselt
4. Martha White
5. A. Mahmood
6. Csaba Szepesvari
7. Yoshua Bengio
8. J. Urgen Schmidhuber

Citations in the corpus

• An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning (2015, methodology): “Sutton, R. S., Maei, H. R., Precup, D., Bhatnagar, S., Silver, D., Szepesvári, Cs., Wiewiora, E. (2009).”
• Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms (2000, background): “The update rule for sarsa(0) (Rummery, 1994; Rummery & Niranjan, 1994; John, 1994, 1995; Singh & Sutton, 1995; Sutton, 1996) is quite similar to Q-learning: Qt+1(st; at) = (1 t(st; at))Qt(st; at) + t(st; at)[rt + Qt(st+1; at+1)]: (3) The main di erence is that Q-learning makes an update based on the”
• Algorithms for Reinforcement Learning (2010, background): “The multi-step extension of SARSA follows along the lines of the similar extension of TD(0), giving rise to the SARSA(λ) algorithm due to Rummery and Niranjan (1994); Rummery (1995).”
• Reinforcement Learning: An Introduction (1998, methodology): “7 Sarsa( ) with accumulating traces was first explored as a control method by Rummery and Niranjan (1994; Rummery, 1995).”