Why did TD-Gammon Work?

By Jordan B. Pollack, Alan D. Blair. 1996

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. Chelsea Finn
5. Shimon Whiteson
6. Timothy P. Lillicrap
7. Nicolas Manfred Otto Heess
8. Yuxi Li

Citations in the corpus

• Playing Atari with Deep Reinforcement Learning (2013, background): “This led to a widespread belief that the TD-gammon approach was a special case that only worked in backgammon, perhaps because the stochasticity in the dice rolls helps explore the state space and also makes the value function particularly smooth [19].”