Real-time learning: a ball on a beam

By Hamid Benbrahim, J. Doleac, Judy A. Franklin, O. Selfridge. 1992

How researchers see this paper

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

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, background): “Example applications include balancing a ball on a beam (Benbrahim et al., 1992), one-DoF ball in a cup (Nemec et al.”
Model-Free reinforcement learning with continuous action in practice (2012, unknown): “The ﬁrst work with real-time reinforcement learning on a conventional mobile robot seems to have been that by Bowling and Veloso in 2003 [7].”
Online Model Learning Algorithms for Actor-Critic Control (2015, background): “In the field of robotics, early successful results of using actor-critic type methods on real hardware were shown on a ball on a beam setup (Benbrahim et al., 1992), a peg-in-hole insertion task (Gullapalli, 1993) and biped locomotion (Benbrahim and Franklin, 1997).”
Policy Gradient Methods for Robotics (2006, methodology): “…1990s, these methods have been applied to a variety of robot learning problems ranging from simple control tasks (e.g., balancing a ball-on a beam [3], and pole-balancing [4]) to complex learning tasks involving many degrees of freedom such as learning of complex motor skills [2], [5], [6] and…”
Reinforcement learning of motor skills with policy gradients (2008, methodology): “colleagues (Benbrahim & Franklin, 1997; Gullapalli, Franklin, & Benbrahim, 1994) in the early 1990s, these methods have been applied to a variety of robot learning problems ranging from simple control tasks (e.g., balancing a ball on a beam ( Benbrahim, Doleac, Franklin, & Selfridge, 1992 ), and pol”
Biped dynamic walking using reinforcement learning (1997, unknown): “When the action space is discrete, the implementation of reinforcement learning is straightforward, [3, 6 ,8].”