2-D Pole Balancing with Recurrent Evolutionary Networks

By Faustino J. Gomez, Risto Miikkulainen. 1998

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. Chelsea Finn
4. Shimon Whiteson
5. J. Urgen Schmidhuber
6. Abhishek Gupta
7. Xi Chen
8. Yan Duan

Citations in the corpus

• Benchmarking Deep Reinforcement Learning for Continuous Control (2016, methodology): “Similar tasks have been explored in Gomez & Miikkulainen (1998); Sch¨afer & Udluft (2005); Heess et al. (2015a); Wierstra et al. (2007).”
• Evolving Modular Fast-Weight Networks for Control (2005, background): “Note that unlike the 2-dimensional version of the classic pole balancer [7], the system cannot be controlled by solving the 1-dimensional case and then using two copies of this controller, one for each principle axis.”
• Real-time neuroevolution in the NERO video game (2005, background): “Using such techniques, relatively simple ANN controllers can be trained in games and game-like environments to produce convincing purposeful and intelligent behavior [5], [11], [36], [40], [65]–[67].”