Decision Tree Function Approximation in Reinforcement Learning

By Larry D. Pyeatt, Adele E. Howe. 1999

How researchers see this paper

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

1. Pablo Hernandez-Leal
2. Bilal Kartal
3. Matthew E. Taylor
4. Peter Stone
5. Mohammad Rostami
6. Haitham Bou-Ammar
7. Sanmit Narvekar
8. Alessandro Lazaric

Citations in the corpus

• A survey and critique of multiagent deep reinforcement learning (2018, methodology): “Function approximators tried to address those limitations, using for example, decision trees [262], tile coding [314], radial basis functions [177], and locally weighted regression [46] to approximate the value function.”
• Closed-Loop Learning of Visual Control Policies (2011, unknown): “Pyeatt and Howe (2001) analyze the performance of several splitting criteria for a variation of Continuous U-Tree.”
• Reinforcement Learning: A Tutorial Survey and Recent Advances (2009, unknown): “Decision trees have also beed used for the same task, and the central idea underlying their use (Chapman and Kaelbling, 1991; Pyeatt and Howe, 1998) is to split the state space, via leaf nodes, into dissimilar grids, and the splitting depends on how often a part of the state space has been visited.”