Swinging up the Acrobot: an example of intelligent control

By Gerald DeJong, Mark W. Spong. 1994

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. Shimon Whiteson
4. Chelsea Finn
5. Yuxi Li
6. Yan Duan
7. Xi Chen
8. Abhishek Gupta

Citations in the corpus

• Benchmarking Deep Reinforcement Learning for Continuous Control (2016, background): “We implement five basic tasks that have been widely analyzed in reinforcement learning and control literature: Cart-Pole Balancing (Stephenson, 1908; Donaldson, 1960; Widrow, 1964; Michie & Chambers, 1968), Cart-Pole Swing Up (Kimura & Kobayashi, 1999; Doya, 2000), Mountain Car (Moore, 1990), Acrobot”
• A Brief Survey of Deep Reinforcement Learning (2017, neutral): “much early work focused on simple, custom MDPs, there shortly emerged control problems that could be used as standard benchmarks for testing new algorithms, such as the Cartpole [5], Acrobot [22] and Mountain Car [74] domains.”
• The Reinforcement Learning Competitions (2010, background): “In addition, three new domains were introduced: the classic Acrobot problem (DeJong and Spong 1994); Octopus Arm (Yekutieli et al. 2005), which earlier appeared in the 2006 benchmarking event; and Infinite Mario, a new domain developed by Markus Persson 4 based on the classic video game.”